BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Halıcıoğlu Data Science Institute - UC San Diego - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Halıcıoğlu Data Science Institute - UC San Diego
X-ORIGINAL-URL:https://datascience.ucsd.edu
X-WR-CALDESC:Events for Halıcıoğlu Data Science Institute - UC San Diego
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20220313T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20221106T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20230312T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20231105T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20240310T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20241103T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230503T140000
DTEND;TZID=America/Los_Angeles:20230503T153000
DTSTAMP:20260606T025924
CREATED:20230501T161933Z
LAST-MODIFIED:20230501T161933Z
UID:10000382-1683122400-1683127800@datascience.ucsd.edu
SUMMARY:Security and Privacy in an Everchanging System Landscape
DESCRIPTION:Abstract: From AI and IoT to AR/VR and Web 3.0\, computer systems are evolving at an unprecedented rate. While this evolution has given rise to exciting applications and opportunities\, it has also brought about novel security and privacy challenges within these systems and across their interactions with existing platforms. In this talk\, I will discuss how system security researchers can keep up with this everchanging landscape and showcase some of my lab’s recent work on understanding and detecting malicious web bots. I will explore how we can build and roll out research infrastructure to measure web bot activities and later use our newfound understanding to develop practical solutions to counter them. I will highlight how we can apply similar research principles to areas such as AI and IoT. Finally\, I will conclude my talk by previewing some of my ongoing work and outlining my research roadmap toward achieving “security at inception” for emerging systems. \nBio: Amir Rahmati is an Assistant Professor in the Department of Computer Science at Stony Brook University\, where he leads the Ethos Security & Privacy lab. He received his Ph.D. in Computer Science & Engineering from the University of Michigan in 2017. His research focuses on understanding emerging threats in computer systems and building practical solutions that can tackle their security and privacy challenges. His work has resulted in tens of publications and patents\, as well as thousands of citations. Rahmati’s research is supported by the Air Force Office of Scientific Research (AFOSR)\, Office of Naval Research (ONR)\, Meta\, and IBM. His research has received frequent attention from media outlets\, including MIT Technology Review\, Washington Post\, and Bloomberg. His work on the security of autonomous driving systems is part of the permanent display at the London Science Museum.
URL:https://datascience.ucsd.edu/event/security-and-privacy-in-an-everchanging-system-landscape/
LOCATION:SDSC\, The Auditorium\, 9836 Hopkins Dr\, La Jolla\, San Diego\, CA\, United States
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230510T140000
DTEND;TZID=America/Los_Angeles:20230510T153000
DTSTAMP:20260606T025924
CREATED:20230509T195847Z
LAST-MODIFIED:20230510T170811Z
UID:10000385-1683727200-1683732600@datascience.ucsd.edu
SUMMARY:Proximal MCMC for Bayesian Inference of Constrained and Regularized Estimation
DESCRIPTION:Abstract: In this talk I will introduce some extensions to the proximal Markov Chain Monte Carlo (Proximal MCMC) – a flexible and general Bayesian inference framework for constrained or regularized parametric estimation. The basic idea of Proximal MCMC is to approximate nonsmooth regularization terms via the Moreau-Yosida envelope. Initial proximal MCMC strategies\, however\, fixed nuisance and regularization parameters as constants\, and relied on the Langevin algorithm for the posterior sampling. We extend Proximal MCMC to the full Bayesian framework with modeling and data-adaptive estimation of all parameters including regularization parameters. More efficient sampling algorithms such as the Hamiltonian Monte Carlo are employed to scale Proximal MCMC to high-dimensional problems. Our proposed Proximal MCMC offers a versatile and modularized procedure for the inference of constrained and non-smooth problems that is mostly tuning parameter free. We illustrate its utility on various statistical estimation and machine learning tasks.
URL:https://datascience.ucsd.edu/event/proximal-mcmc-for-bayesian-inference-of-constrained-and-regularized-estimation/
LOCATION:SDSC\, The Auditorium\, 9836 Hopkins Dr\, La Jolla\, San Diego\, CA\, United States
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230511T120000
DTEND;TZID=America/Los_Angeles:20230511T140000
DTSTAMP:20260606T025924
CREATED:20230403T224301Z
LAST-MODIFIED:20230407T172325Z
UID:10000373-1683806400-1683813600@datascience.ucsd.edu
SUMMARY:Just Opt Out? Lessons Learned From a Decade of Evasion
DESCRIPTION:Abstract: With the rise of techlash\, an increasing number of users wish they could just say no to data tracking\, surveillance capitalism\, and the socially divisive effects of creepy technologies in our daily lives. But can we truly walk away from these systems? And what do we learn when we do? In this talk\, Vertesi tells the zany stories and practical tips that emerged from my extreme experiments in living digitally off Big Tech’s grid. Vertesi uncovers the sociological mechanisms that fuel these companies’ effective monetization of our lives and shares the hard-won tools and fresh insights Vertesi developed to help us all disable toxic tech and restore our right to choose.\n\nBio: Dubbed “Margaret Mead among the Starfleet” in the Times Literary Supplement\, Janet Vertesi is an associate professor of Sociology at Princeton University. She has spent fifteen years embedded with NASA’s robotic spacecraft teams as a sociologist of science and technology. Her publications range from the books Shaping Science and Seeing Like a Rover (both University of Chicago Press)\, edited collections digitalSTS (Princeton Press) and Representation in Scientific Practice Revisited (MIT Press)\, and top ranked journals and conference proceedings in the fields of the sociology of science and technology\, and human-computer and human-robot interaction. Currently co-editor of MIT Press’ Infrastructures series\, Vertesi is well known for her “Opt Out Experiments” evading capture in the personal data economy\, including a famous obfuscated pregnancy and trip to Disneyland. More at http://janet.vertesi.comand https://optoutproject.net\n\nThe meeting will be held in person at PEB 721\, on the 7th floor of the UC San Diego Social Sciences Public Engagement Building. Lunch will be served. Vegan\, vegetarian\, and gluten-free options will be available. Kindly RSVP by May 9 at 2 p.m. if you are planning to attend (limited number of seats available!).\n\nRSVP here
URL:https://datascience.ucsd.edu/event/just-opt-out-lessons-learned-from-a-decade-of-evasion/
LOCATION:Public Engagement Building (PEB) 721\, 9625 Scholars Drive North MC 0305\, La Jolla\, CA\, 92093\, United States
CATEGORIES:Guest Lecture
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230517T120000
DTEND;TZID=America/Los_Angeles:20230517T133000
DTSTAMP:20260606T025924
CREATED:20230512T225134Z
LAST-MODIFIED:20230512T234954Z
UID:10000386-1684324800-1684330200@datascience.ucsd.edu
SUMMARY:Earth & Ocean Image Processing Made Easy with MATLAB - Lunch and Learn
DESCRIPTION:In our continued collaboration with UCSD\, we are pleased to announce our spring seminar topic! Join us for a lunch-n-learn technical seminar from our MathWorks team on image processing with MATLAB! MathWorks is looking to create a connection point for conversations about the landscape of computational languages – and the broader impact that software has in academia and industry today. \n\n\n\n\nBring your questions about the landscape of computational tools and topics such as managing data\, climate change\, image processing\, and more! This session will also include a section on career paths for engineers and scientists – our engineers will share a bit about their personal education and career trajectory – and what technical skills can support your own career paths! \nFollow this link to register as seats are limited! Lunch will be provided. \n  \n\n\n\n\nEarth & Ocean Image Processing Made Easy with MATLAB \nThere is a very rich and sophisticated ecosystem today for advanced image processing\, ranging from complex computer vision techniques to AI/machine learning applications. MATLAB is a popular tool used by research and development engineers in many imaging applications. It’s used for a variety of tasks from analyzing\, enhancing\, and visualizing images to developing advanced imaging algorithms deployed on PCs\, embedded systems\, and the cloud. \nThis session explores the basics of pixel-level image processing and high-level machine learning models in MATLAB for images. Some of the tasks we will work through include: \n\nImporting various image and Landsat files\nNew Apps in MATLAB for Imaging: Introduction to apps and features to simplify image dataexploration\, processing\, visualization\, and algorithm development\nBasics of machine learning models for image classification\nProcess\, analyze data\, and map data\, creating .shp (GIS) files and publication-ready figures.\n\n  \nPresented by: Laura Sammon \n\n\n\nLaura is a Customer Success Engineer at MathWorks. She supports teaching and research across science and engineering disciplines\, specializing in coding applications for Earth and ocean science. Laura earned her Ph.D. in Geology from the University of Maryland where she studied the composition of Earth’s crust and interior through geochemical and geophysical data.
URL:https://datascience.ucsd.edu/event/earth-ocean-image-processing-made-easy-with-matlab-lunch-and-learn/
LOCATION:Vaughan Hall\, Room 100\, (UCSD-SIO) 8629 Kennel Way\, La Jolla\, CA\, 92037\, United States
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230518T120000
DTEND;TZID=America/Los_Angeles:20230518T140000
DTSTAMP:20260606T025924
CREATED:20230512T234520Z
LAST-MODIFIED:20230512T235340Z
UID:10000387-1684411200-1684418400@datascience.ucsd.edu
SUMMARY:UC San Diego & MathWorks | Research & Curriculum Micro Symposium
DESCRIPTION:A series of lightning talks will be presented highlighting collaborative efforts between UC San Diego and MathWorks via series of supported research and curriculum projects. Join us to learn how each project team are crossing boundaries and using MATLAB & Simulink in their work in areas such as Data Science\, Oceanography\, and various Engineering disciplines! \nJoin us for lunch and lightning talks: \n\nWe will have speakers from JSOE\, HDSI and Scripps who will share their MATLAB uses in teaching\, projects and research.\nThe opportunity to talk to the MathWorks team about the tools they provide – learn about what’s new and ask your questions here!\nAn opportunity to network with your fellow UC San Diego colleagues from other departments!\n\n\n\n\n\nRegister Here – seats are limited and lunch will be provided! \nLocation: Qualcomm Conference Center at JSOE\nTime: May 18th\, 2023\, 12pm – 2pm \n\n\n\n\n  \nADDITIONAL RESOURCES: \nLearn about job openings/career opportunities here  \nVisit MathWorks/UC San Diego collaboration website
URL:https://datascience.ucsd.edu/event/uc-san-diego-mathworks-research-curriculum-micro-symposium/
LOCATION:Qualcomm Conference Room at JSOE\, Jacobs Hall\, 9736 Engineers Ln\, La Jolla\, San Diego\, CA\, 92093\, United States
CATEGORIES:Symposium
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230518T140000
DTEND;TZID=America/Los_Angeles:20230518T150000
DTSTAMP:20260606T025924
CREATED:20230323T181111Z
LAST-MODIFIED:20230513T000759Z
UID:10000364-1684418400-1684422000@datascience.ucsd.edu
SUMMARY:Scaling and Generalizing Approximate Bayesian Inference | David Blei
DESCRIPTION:Abstract: A core problem in statistics and machine learning is to approximate difficult-to-compute probability distributions. This problem is especially important in Bayesian statistics\, which frames all inference about unknown quantities as a calculation about a conditional distribution. In this talk I review and discuss innovations in variational inference (VI)\, a method that approximates probability distributions through optimization. VI has been used in myriad applications in machine learning and Bayesian statistics. It tends to be faster than more traditional methods\, such as Markov chain Monte Carlo sampling. \nAfter quickly reviewing the basics\, I will discuss two lines of research in VI. I first describe stochastic variational inference\, an approximate inference algorithm for handling massive datasets\, and demonstrate its application to probabilistic topic models of millions of articles. Then I discuss black box variational inference\, a generic algorithm for approximating the posterior. Black box inference easily applies to many models but requires minimal mathematical work to implement. I will demonstrate black box inference on deep exponential families—a method for Bayesian deep learning—and describe how it enables powerful tools for probabilistic programming. \n  \nBio: David Blei is a Professor of Statistics and Computer Science at Columbia University\, and a member of the Columbia Data Science\nInstitute. He studies probabilistic machine learning\, including its theory\, algorithms\, and application. David has received several awards for his research. He received a Sloan Fellowship (2010)\, Office of Naval Research Young Investigator Award (2011)\, Presidential Early Career Award for Scientists and Engineers (2011)\, Blavatnik Faculty Award (2013)\, ACM-Infosys Foundation Award (2013)\, a Guggenheim fellowship (2017)\, and a Simons Investigator Award (2019). He is the co-editor-in-chief of the Journal of Machine Learning Research. He is a fellow of the ACM and the IMS. \nWebsite : http://www.cs.columbia.edu/~blei/ \n  \nZoom Link : http://bit.ly/HDSI-Seminars
URL:https://datascience.ucsd.edu/event/david-blei/
LOCATION:SDSC\, The Auditorium\, 9836 Hopkins Dr\, La Jolla\, San Diego\, CA\, United States
CATEGORIES:Colloquium,Guest Lecture
ATTACH;FMTTYPE=image/jpeg:https://datascience.ucsd.edu/wp-content/uploads/2023/03/professordavisblei_headshot-scaled.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230519T120000
DTEND;TZID=America/Los_Angeles:20230519T140000
DTSTAMP:20260606T025924
CREATED:20230403T224454Z
LAST-MODIFIED:20230407T172236Z
UID:10000374-1684497600-1684504800@datascience.ucsd.edu
SUMMARY:Beyond 'The Algorithm': Fields\, Drama\, and Extreme Content Among Vegan Influencers
DESCRIPTION:Abstract: Existing research on polarization on social media platforms emphasizes the role of algorithmic “filter bubbles” and platform failure in amplifying extreme attitudes among online audiences. This article provides a different approach by focusing on online creators rather than audiences. Christin adapts field theory to examine the dynamics structuring exchanges between social media influencers\, which she analyzes as contentious position-takings within fields created and mediated by social media platforms. To demonstrate the relevance of this framework\, Christin draws on a qualitative study of vegan influencers on YouTube and Instagram. Two pathways shape the structuration of fields of social media production: drama\, or highly publicized scandals and interpersonal conflicts between influencers; and extreme content\, in which influencers and users reinforce their shared worldviews through niche and inflammatory content. Christin concludes by discussing the relevance of field theory for the study of social media and online disinformation more broadly.\n\n\nBiography: Angèle Christin is an assistant professor in the Department of Communication and affiliated faculty in the Sociology Department\, the Program in Science\, Technology\, and Society\, and the Center for Work\, Technology\, and Organization at Stanford University. She studies how algorithms and analytics transform professional values\, expertise\, and work practices.\n\n\nThe meeting will be held in person at PEB 721\, on the 7th floor of the UC San Diego Social Sciences Public Engagement Building. Lunch will be served. Vegan\, vegetarian\, and gluten-free options will be available. Kindly RSVP by May 17 at 2 p.m. if you are planning to attend (limited number of seats available!).\n\nRSVP here
URL:https://datascience.ucsd.edu/event/beyond-the-algorithm-fields-drama-and-extreme-content-among-vegan-influencers/
LOCATION:Public Engagement Building (PEB) 721\, 9625 Scholars Drive North MC 0305\, La Jolla\, CA\, 92093\, United States
CATEGORIES:Guest Lecture
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230522T130000
DTEND;TZID=America/Los_Angeles:20230522T143000
DTSTAMP:20260606T025924
CREATED:20230523T143630Z
LAST-MODIFIED:20230523T143643Z
UID:10000388-1684760400-1684765800@datascience.ucsd.edu
SUMMARY:Algorithms for multi-group learning
DESCRIPTION:Abstract: Multi-group agnostic learning is a formal learning criterion that is concerned with the conditional risks of predictors within subgroups of a population. The criterion addresses recent practical concerns such as subgroup fairness and hidden stratification. I’ll talk about the structure of solutions to the multi-group learning problem\, as well as some simple and near-optimal algorithms for the learning problem. This is based on joint work with Christopher Tosh.
URL:https://datascience.ucsd.edu/event/algorithms-for-multi-group-learning/
LOCATION:SDSC\, The Synthesis Center\, 9500 Gilman Drive\, La Jolla\, CA\, 92093\, United States
CATEGORIES:Colloquium
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230524T120000
DTEND;TZID=America/Los_Angeles:20230524T150000
DTSTAMP:20260606T025924
CREATED:20230503T030808Z
LAST-MODIFIED:20230503T030808Z
UID:10000383-1684929600-1684940400@datascience.ucsd.edu
SUMMARY:Housing Fair : A Community Effort
DESCRIPTION:
URL:https://datascience.ucsd.edu/event/housing-fair-a-community-effort/
LOCATION:Library Walk
CATEGORIES:Mixer,Social Event
ATTACH;FMTTYPE=image/jpeg:https://datascience.ucsd.edu/wp-content/uploads/2023/05/OPTION-1-IG-e1683083080841.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230524T140000
DTEND;TZID=America/Los_Angeles:20230524T150000
DTSTAMP:20260606T025924
CREATED:20230323T181207Z
LAST-MODIFIED:20240402T224726Z
UID:10000365-1684936800-1684940400@datascience.ucsd.edu
SUMMARY:Spectral clustering in high-dimensional Gaussian mixture block models
DESCRIPTION:The Gaussian mixture block model is a simple generative model for networks: to generate a sample\, we associate each node with a latent feature vector sampled from a mixture of Gaussians\, and we add an edge between nodes if and only if their feature vectors are sufficiently similar. The different components of the Gaussian mixture represent the fact that there may be several types of nodes with different distributions over features — for example\, in a social network each component represents the different attributes of a distinct community. In this talk I will discuss recent results on the performance of spectral clustering algorithms on networks sampled from high-dimensional Gaussian mixture block models\, where the dimension of the latent feature vectors grows as the size of the network goes to infinity. Our results merely begin to sketch out the information-computation landscape for clustering in these models\, and I will make an effort to emphasize open questions.\nBased on joint work with Shuangping Li.
URL:https://datascience.ucsd.edu/event/tselil-schramm/
LOCATION:SDSC\, The Synthesis Center\, 9500 Gilman Drive\, La Jolla\, CA\, 92093\, United States
CATEGORIES:Colloquium
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230530T140000
DTEND;TZID=America/Los_Angeles:20230530T153000
DTSTAMP:20260606T025924
CREATED:20230530T153018Z
LAST-MODIFIED:20230530T153018Z
UID:10000389-1685455200-1685460600@datascience.ucsd.edu
SUMMARY:Representation Learning: A Causal Perspective
DESCRIPTION:Abstract: Representation learning constructs low-dimensional representations to summarize essential features of high-dimensional data like images and texts. Ideally\, such a representation should efficiently capture non-spurious features of the data. It shall also be disentangled so that we can interpret what feature each of its dimensions captures. However\, these desiderata are often intuitively defined and challenging to quantify or enforce. \nIn this talk\, we take on a causal perspective of representation learning. We show how desiderata of representation learning can be formalized using counterfactual notions\, enabling metrics and algorithms that target efficient\, non-spurious\, and disentangled representations of data. We discuss the theoretical underpinnings of the algorithm and illustrate its empirical performance in both supervised and unsupervised representation learning.
URL:https://datascience.ucsd.edu/event/representation-learning-a-causal-perspective/
LOCATION:SDSC\, The Auditorium\, 9836 Hopkins Dr\, La Jolla\, San Diego\, CA\, United States
CATEGORIES:Colloquium
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230531T140000
DTEND;TZID=America/Los_Angeles:20230531T153000
DTSTAMP:20260606T025924
CREATED:20230530T153213Z
LAST-MODIFIED:20230530T153213Z
UID:10000390-1685541600-1685547000@datascience.ucsd.edu
SUMMARY:On the complexity of Frank-Wolfe methods
DESCRIPTION:Abstract: Frank-Wolfe methods are popular for optimization over a polytope. One of the reasons is because they do not need projection onto the polytope but only linear optimization over it. This talk has two parts. \nThe first part will be about the complexity of Wolfe’s method\, an algorithm closely related to Frank-Wolfe methods. In 1974 Phillip Wolfe proposed a method to find the minimum Euclidean-norm point in a convex polyhedron. The method is essentially the same as the Lawson-Hanson algorithm for non-negative least squares. The complexity of Wolfe’s method has remained unknown since he proposed it. The method is important because it is used as a subroutine for one of the most practical algorithms for submodular function minimization. We present the first example that Wolfe’s method takes exponential time. Additionally\, we improve previous results to show that linear programming reduces in strongly-polynomial time to the minimum norm point problem over a simplex. \nThe second part will be about the smoothed complexity of Frank-Wolfe methods. To understand their complexity\, a fruitful approach in many\nworks has been the use of condition measures of polytopes. Lacoste-Julien and Jaggi introduced a condition number for polytopes and showed linear convergence for several variations of the method. The actual running time can still be exponential in the worst case (when the condition number is exponential). We study the smoothed complexity of the condition number\, namely the condition number of small random perturbations of the input polytope and show that it is polynomial for any simplex and exponential for general polytopes. Our argument for polytopes is a refinement of an argument that we develop to study the conditioning of random matrices. The basic argument shows that for c > 1\, a d-by-n random Gaussian matrix with n >= cd has a d-by-d submatrix with minimum singular value that is exponentially small with high probability. This also has consequences on known results about the robust uniqueness of tensor decompositions\, the complexity of the simplex method and the diameter of polytopes.
URL:https://datascience.ucsd.edu/event/on-the-complexity-of-frank-wolfe-methods/
LOCATION:SDSC\, The Auditorium\, 9836 Hopkins Dr\, La Jolla\, San Diego\, CA\, United States
CATEGORIES:Colloquium
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230602T100000
DTEND;TZID=America/Los_Angeles:20230602T120000
DTSTAMP:20260606T025924
CREATED:20230505T060339Z
LAST-MODIFIED:20230505T060339Z
UID:10000384-1685700000-1685707200@datascience.ucsd.edu
SUMMARY:HDSI 2023 Undergraduate Scholarship Showcase
DESCRIPTION:The Halıcıoğlu Data Science Institute is preparing to host our annual Undergraduate Scholarship Showcase. We invite you to join our scholarship cohort in an interactive presentation of the projects they have worked on for the past academic year. \n> View Project List Here < \nWe will be sending the RSVP form with the Zoom meeting link within the next week. Please be sure to monitor your email for additional updates\, and reach out to us at dscstudent@ucsd.edu if you have any questions or concerns.
URL:https://datascience.ucsd.edu/event/hdsi-2023-undergraduate-scholarship-showcase/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230605T080000
DTEND;TZID=America/Los_Angeles:20230605T170000
DTSTAMP:20260606T025924
CREATED:20230613T210741Z
LAST-MODIFIED:20230613T213829Z
UID:10000393-1685952000-1685984400@datascience.ucsd.edu
SUMMARY:5-Year Anniversary Celebration & Ribbon Cutting
DESCRIPTION:On June 5th\, 2023 the Halıcıoğlu Data Science Institute celebrated the 5-year anniversary since becoming its own academic department. In parallel to these celebrations\, HDSI unveiled it’s first dedication space\, the Halıcıoğlu Data Science Institute building. \n  \n[ngg src=”galleries” ids=”1″ display=”basic_thumbnail” thumbnail_crop=”0″ images_per_page=”15″] 
URL:https://datascience.ucsd.edu/event/5-year-anniversary-celebration-ribbon-cutting/
LOCATION:3234 Matthews Ln\, La Jolla\, 92093\, United States
CATEGORIES:HDSI Event
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230606T130000
DTEND;TZID=America/Los_Angeles:20230606T140000
DTSTAMP:20260606T025924
CREATED:20230601T065512Z
LAST-MODIFIED:20230601T070105Z
UID:10000391-1686056400-1686060000@datascience.ucsd.edu
SUMMARY:Samuel Lau | Instructor-Centered Design of Tools to Support Teaching Programming and Data Science At Scale
DESCRIPTION:Abstract \nInstructors of technical subjects like programming and data science use a wide array of software tools that enable them to create sophisticated and engaging lessons at scale. Although there are many such tools available\, instructors often find themselves repurposing software originally designed for other people\, like professional software engineers. This mismatch of intent adds extra logistical complexity to the already-challenging task of designing and delivering effective learning content. \nTo address these issues\, this dissertation takes an instructor-centered approach. It surfaces previously unmet needs through studies of instructors\, their goals\, and their software tools. The key findings are that instructors constantly seek to update their learning materials\, yet encounter heavy logistical challenges in doing so because the tools they use to help design their lessons were not intended for instructional use. \nThis dissertation also contributes novel interactive systems that directly support teaching by designing for instructor needs. In particular\, this dissertation contributes program visualization tools that enable instructors to show how code transforms data: TweakIt helps learners work with unfamiliar code snippets\, and the Pandas/Tidy Data/SQL Tutors automatically visualize code that manipulates data tables step-by-step. Together\, this dissertation provides the first evidence that the insights gathered from an instructor-centered approach can lead to tools that better support the work of instruction. \n  \nCommittee members: \nPhilip J. Guo\, Chair\, Cognitive Science \nJames D. Hollan\, Cognitive Science \nRanjit Jhala\, Computer Science and Engineering \nBradley Voytek\, Cognitive Science \nHaijun Xia\, Cognitive Science \n. \nDate & Time : Tuesday\, June 6th\, 1:00pm – 2:00pm \nLocation : Design and Innovation Building\, Room 406 or Join with Zoom
URL:https://datascience.ucsd.edu/event/instructor-centered-design-of-tools-to-support-teaching-programming-and-data-science-at-scale-samuel-lau/
LOCATION:Design & Innovation Building\, Room 406
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230609T150000
DTEND;TZID=America/Los_Angeles:20230609T160000
DTSTAMP:20260606T025924
CREATED:20230605T233443Z
LAST-MODIFIED:20230914T164123Z
UID:10000392-1686322800-1686326400@datascience.ucsd.edu
SUMMARY:Deep Latent Variable Models for Compression and Natural Science | Stephan Mandt
DESCRIPTION:Abstract: Latent variable models have been an integral part of probabilistic machine learning\, ranging from simple mixture models to variational autoencoders to powerful diffusion probabilistic models at the center of recent media attention. Perhaps less well-appreciated is the intimate connection between latent variable models and data compression\, and the potential of these models for advancing natural science. This talk will explore these topics. I will begin by showcasing connections between variational methods and the theory and practice of neural data compression. On the applied side\, variational methods lead to machine-learned compressors of data such as images and videos and offer principled techniques for enhancing their compression performance\, as well as reducing their decoding complexity. On the theory side\, variational methods also provide scalable bounds on the fundamental compressibility of real-world data\, such as images and particle physics data. Lastly\, I will also delve into climate science projects\, where a combination of deep latent variable modeling and vector quantization enables assessing distribution shifts induced by varying climate models and the effects of global warming. \nBio: Stephan Mandt is an Associate Professor of Computer Science and Statistics at the University of California\, Irvine. From 2016 until 2018\, he was a Senior Researcher and Head of the statistical machine learning group at Disney Research in Pittsburgh and Los Angeles. He held previous postdoctoral positions at Columbia University and Princeton University. Stephan holds a Ph.D. in Theoretical Physics from the University of Cologne in Germany\, where he received the National Merit Scholarship. He received the NSF CAREER Award\, a Kavli Fellowship of the U.S. National Academy of Sciences\, the German Research Foundation’s Mercator Fellowship\, and the UCI ICS Mid-Career Excellence in Research Award. He is a member of the ELLIS Society and a former visiting researcher at Google Brain. Stephan will serve as Program Chair of the AISTATS 2024 conference\, currently serves as an Action Editor for JMLR and TMLR\, and frequently serves as Area Chair for NeurIPS\, ICML\, AAAI\, and ICLR.
URL:https://datascience.ucsd.edu/event/deep-latent-variable-models-for-compression-and-natural-science-stephan-mandt/
LOCATION:Computer Science & Engineering Building (CSE)\, Room 1202
CATEGORIES:Colloquium
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230626T120000
DTEND;TZID=America/Los_Angeles:20230626T130000
DTSTAMP:20260606T025924
CREATED:20230629T160446Z
LAST-MODIFIED:20230629T160646Z
UID:10000396-1687780800-1687784400@datascience.ucsd.edu
SUMMARY:The Emergence of General AI for Medicine | Dr. Peter Lee
DESCRIPTION:Dr. Peter Lee is Corporate Vice President of Research and Incubations at Microsoft where he leads Microsoft Research and incubates new research-powered products and lines of business in areas such as artificial intelligence\, computing foundations\, health\, and life sciences. He speaks and writes widely on science and technology trends\, including the attached NEJM article “Benefits\, Limits\, and Risks of GPT-4 as an AI Chatbot for Medicine” and recently published a book with Dr. Isaac Kohane\, “The AI Revolution in Medicine: GPT-4 and Beyond.” \nBefore joining Microsoft in 2010\, he was at DARPA\, where he established a new technology office that created operational capabilities in machine learning\, data science\, and computational social science. Prior to that\, he was a professor and the head of the computer science department at Carnegie Mellon University. Dr. Lee is a member of the National Academy of Medicine and serves on the Boards of Directors of several institutes for the Allen Institute for Artificial Intelligence\, the Brotman Baty Institute for Precision Medicine\, and the Kaiser Permanente Bernard J. Tyson School of Medicine. He served on President Obama’s Commission on Enhancing National Cybersecurity and led studies for PCAST and the National Academies. He has testified before both the US House Science and Technology Committee and the US Senate Commerce Committee.
URL:https://datascience.ucsd.edu/event/the-emergence-of-general-ai-for-medicine-dr-peter-lee/
LOCATION:SDSC\, The Auditorium\, 9836 Hopkins Dr\, La Jolla\, San Diego\, CA\, United States
CATEGORIES:Guest Lecture
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230805T180000
DTEND;TZID=America/Los_Angeles:20230805T210000
DTSTAMP:20260606T025924
CREATED:20230616T085435Z
LAST-MODIFIED:20230616T170852Z
UID:10000395-1691258400-1691269200@datascience.ucsd.edu
SUMMARY:HDSI Alumni Celebration
DESCRIPTION:If you are a HDSI alumni\, faculty or staff\, you’re invited to join us in celebrating and socializing with HDSI alumni this summer when we gather for our annual celebration!  \nREGISTER HERE \nRegistration is 18$ which includes a food\, a free drink\, and more! \nThe registration deadline is July 28th. \nPlease note that registration is required and that this is a private event for HDSI alumni\, and HDSI faculty & staff only. \n  \nThank you for all that you do in educating so many young professionals. We hope to see you on August 5th! 
URL:https://datascience.ucsd.edu/event/hdsi-alumni-celebration/
LOCATION:Ridgewalk Social\, University of California San Diego\, Rimac Annex\, San Diego\, 92093
CATEGORIES:HDSI Event,Social Event
ATTACH;FMTTYPE=image/png:https://datascience.ucsd.edu/wp-content/uploads/2023/06/hdsi-alumni-celeb-e1686905645343.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230914T100000
DTEND;TZID=America/Los_Angeles:20230914T130000
DTSTAMP:20260606T025924
CREATED:20230818T062040Z
LAST-MODIFIED:20230818T062843Z
UID:10000398-1694685600-1694696400@datascience.ucsd.edu
SUMMARY:Causal Inference symposium
DESCRIPTION:Curious about Causality? \nCausality is increasingly a part of AI\, data science\, robotics\, and more\, but it is not always clear how we can learn causality from data. Halıcıoğlu Data Science Institute (HDSI) will be hosting a Causal Inference symposium featuring leading HDSI Faculty who will be providing an introductory overview on these methods\, followed by domain-specific talks and open discussion. \nWe welcome all UCSD faculty\, graduate students\, HDSI industry partners\, and guests to join us. \nRegister here: https://www.eventbrite.com/e/causality-symposium-tickets-677459017157?aff=oddtdtcreator  \n\n\n\n\nPlease complete your registration by Friday\, Sept. 8\, 2023. \n\n\n\n\n \nEvent details\n\nDate: September 14\, 2023\nTime: 10:00 am\nLocation: Halıcıoğlu Data Science Institute\, Room 123 (Multipurpose Room)\n\n  \nAgenda \n\n9:30 am – 10 am: Check-in & Coffee\n10 am – 10:30 am: Welcome Remarks & Causality Overview – David Danks\n10:30 am – 11:50 am: Faculty Presentations \n\nCausal Inference for Responsible and Reliable Data Science – Babak Salimi\nRobust Causal Inference with Complex Datasets – Jelena Bradic\nDemystifying Neural Networks Through Interpretable Neurons – Lily Weng\nAdvancing Machine Intelligence Through Learning and Using Causal Knowledge – Biwei Huang\n\n\n11:50 am – 12 pm: Break\n12 pm – 1 pm: Discussion Session\n\nLunch will be provided afterwards. 
URL:https://datascience.ucsd.edu/event/causal-inference-symposium/
LOCATION:3234 Matthews Ln\, La Jolla\, 92093\, United States
CATEGORIES:Symposium
ATTACH;FMTTYPE=image/png:https://datascience.ucsd.edu/wp-content/uploads/2023/08/Event-Flyer-1-e1692339619192.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20231002T140000
DTEND;TZID=America/Los_Angeles:20231002T150000
DTSTAMP:20260606T025924
CREATED:20230919T181539Z
LAST-MODIFIED:20230919T181539Z
UID:10000399-1696255200-1696258800@datascience.ucsd.edu
SUMMARY:Some new results for streaming principal component analysis
DESCRIPTION:Abstract: While streaming PCA (also known as Oja’s algorithm) was proposed about four decades ago and has roots going back to 1949\, theoretical resolution in terms of obtaining optimal convergence rates has been obtained only in the last decade. However\, we are not aware of any available distributional guarantees\, which can help provide confidence intervals on the quality of the solution. In this talk\, I will present the problem of quantifying uncertainty for the estimation error of the leading eigenvector using Oja’s algorithm for streaming PCA\, where the data are generated IID from some unknown distribution. Combining classical tools from the U-statistics literature with recent results on high-dimensional central limit theorems for quadratic forms of random vectors and concentration of matrix products\, we establish a distributional approximation result for the error between the population eigenvector and the output of Oja’s algorithm. We also propose an online multiplier bootstrap algorithm and establish conditions under which the bootstrap distribution is close to the corresponding sampling distribution with high probability. While there are optimal rates for the streaming PCA problem\, they typically apply to the IID setting\, whereas in many applications like distributed optimization\, the data is generated from a Markov chain and the goal is to infer parameters of the limiting stationary distribution. If time permits\, I will also present our near-optimal finite sample guarantees which remove the logarithmic dependence on the sample size in previous work\, where Markovian data is downsampled to get a nearly independent data stream. \nBio: Purnamrita Sarkar is an associate professor of Statistics at the University of Texas at Austin. Their interests are in the intersection of asymptotic statistics\, scalable algorithms and networks and recently on uncertainty estimation for streaming algorithms and resampling methods for networks. Dr. Sarkar is affiliated with the AI institute and EnCORE: Institute for Emerging CORE Methods of Data Science. They were a postdoctoral scholar at the University of California\, Berkeley working on asymptotic theory for network models and the nonparametric bootstrap for big data. Dr\, Sarkar earned their PhD from the Machine Learning Department at Carnegie Mellon University\n 
URL:https://datascience.ucsd.edu/event/some-new-results-for-streaming-principal-component-analysis/
LOCATION:3234 Matthews Ln\, La Jolla\, 92093\, United States
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20231004T093000
DTEND;TZID=America/Los_Angeles:20231004T103000
DTSTAMP:20260606T025924
CREATED:20231002T164337Z
LAST-MODIFIED:20231004T165423Z
UID:10000400-1696411800-1696415400@datascience.ucsd.edu
SUMMARY:Fireside Chat: Theory in the age of modern AI
DESCRIPTION:TILOS Fireside Chat on “Theory in the age of modern AI“\, which will be a conversation led by TILOS team members: Misha Belkin (UCSD)\, Arya Mazumdar (moderator\, UCSD)\, Tara Javidi (UCSD)\, Visheeth Vishnoi (Yale U). The focus will be on the implications to\, and the roles played by theory\, in modern AI (especially with the recent exciting development in LLMs).  \n***************** \nTitle: TILOS Fireside Chat on Theory in the age of modern AI \nPanelists: Misha Belkin (UCSD)\, Arya Mazumdar(moderator\, UCSD)\, Tara Javidi (UCSD)\, Visheeth Vishnoi (Yale U) \nTime: Oct 4 (Wed) @ 9:30am — 10:00am PT / 12:30pm — 1:30pm ET
URL:https://datascience.ucsd.edu/event/tilos-fireside-chat-theory-in-the-age-of-modern-ai/
LOCATION:3234 Matthews Ln\, La Jolla\, 92093\, United States
CATEGORIES:Fireside Chat
ATTACH;FMTTYPE=image/png:https://datascience.ucsd.edu/wp-content/uploads/2023/10/TILOS-Square_HDSI-Website-e1712854679822.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20231011T100000
DTEND;TZID=America/Los_Angeles:20231011T110000
DTSTAMP:20260606T025925
CREATED:20231002T224704Z
LAST-MODIFIED:20231011T171144Z
UID:10000402-1697018400-1697022000@datascience.ucsd.edu
SUMMARY:TILOS Seminar: Towards Foundation Models for Graph Reasoning and AI 4 Science
DESCRIPTION:TILOS Seminar: Towards Foundation Models for Graph Reasoning and AI 4 Science\n\n\nMichael Galkin\, Research Scientist at AI Lab\nHDSI 123 and Zoom: https://ucsd.zoom.us/j/99334315002 \nAbstract: Foundation models in graph learning are hard to design due to the lack of common invariances that transfer across different structures and domains. In this talk\, I will give an overview of the two main tracks of my research at Intel AI: creating foundation models for knowledge graph reasoning that can run zero-shot inference on any multi-relational graphs\, and foundation models for materials discovery in the AI4Science domain that capture physical properties of crystal structures and transfer to a variety of predictive and generative tasks. We will also talk about theoretical and practical challenges like scaling behavior\, data scarcity\, and diverse evaluation of foundation graph models. \nBio: Michael Galkin is a Research Scientist at Intel AI Lab in San Diego working on Graph Machine Learning and Geometric Deep Learning. Previously\, he was a postdoc at Mila – Quebec AI Institute with Will Hamilton\, Reihaneh Rabbany\, and Jian Tang\, focusing on many graph representation learning problems. Sometimes\, Mike writes long blog posts on Medium about graph learning.
URL:https://datascience.ucsd.edu/event/tilos-seminar-towards-foundation-models-for-graph-reasoning-and-ai-4-science/
LOCATION:3234 Matthews Ln\, La Jolla\, 92093\, United States
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/png:https://datascience.ucsd.edu/wp-content/uploads/2023/10/TILOS-Square_HDSI-Website-e1712854679822.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20231011T110000
DTEND;TZID=America/Los_Angeles:20231011T123000
DTSTAMP:20260606T025925
CREATED:20231004T162521Z
LAST-MODIFIED:20231010T235034Z
UID:10000404-1697022000-1697027400@datascience.ucsd.edu
SUMMARY:EGEMEN KOLEMEN | SEMINAR ON FUSION ENERGY AND AI/ML JOINT SEMINAR: CSE\, HDSI\, MAE\, SDSC
DESCRIPTION:SEMINAR ON FUSION ENERGY AND AI/MLJOINT SEMINAR: CSE\, HDSI\, MAE\, SDSCEGEMEN KOLEMENPRINCETON UNIVERSITY \nAbstract: Recent advances in computing hardware (FPGAs\,distributed parallel computing) and numerical methods (machinelearning algorithms\, automatic differentiation) create newpossibilities for Fusion Power Plant optimization and control. Inthis talk\, I will discuss some of the recent accomplishments of thePlasma Control Group at Princeton that take advantage of thesenew capabilities.BIO: Egemen Kolemen is an Associate Professor at PrincetonUniversity’s Mechanical & Aerospace Engineering department\,jointly appointed with the Andlinger Center for Energy and theEnvironment and the Princeton Plasma Physics Laboratory (PPPL).
URL:https://datascience.ucsd.edu/event/egemen-kolemen-seminar-on-fusion-energy-and-ai-ml-joint-seminar-cse-hdsi-mae-sdsc/
CATEGORIES:Seminar
ORGANIZER;CN="SDSC - San Diego Supercomputer Center":MAILTO:https://www.sdsc.edu/
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20231011T140000
DTEND;TZID=America/Los_Angeles:20231011T153000
DTSTAMP:20260606T025925
CREATED:20231003T171716Z
LAST-MODIFIED:20231004T200415Z
UID:10000403-1697032800-1697038200@datascience.ucsd.edu
SUMMARY:Steampunk Data Science
DESCRIPTION:Abstract: How did scientists make sense of data before statistics and computing? This talk will explore this question by focusing on the discovery of vitamins\, which occurred in the early 20th century just before the advent of modern statistical methodology. I will describe the varied practices in experimentation and reporting and highlight the sorts of insights required to uncover what “works.” Through this discussion\, I will draw connections to contemporary data science tools to illustrate their pros and cons in facilitating discovery. \nBio: Benjamin Recht is a Professor in the Department of Electrical Engineering and Computer Sciences at the University of California\, Berkeley. His research has focused on applying mathematical optimization and statistics to problems in data analysis and machine learning. He is currently studying histories\, methods\, and theories of scientific validity and experimental design.
URL:https://datascience.ucsd.edu/event/steampunk-data-science/
LOCATION:3234 Matthews Ln\, La Jolla\, 92093\, United States
CATEGORIES:Guest Lecture,Seminar
ATTACH;FMTTYPE=image/png:https://datascience.ucsd.edu/wp-content/uploads/2023/10/benrecht-social-flyer.png
END:VEVENT
BEGIN:VEVENT
DTSTART;VALUE=DATE:20231012
DTEND;VALUE=DATE:20231013
DTSTAMP:20260606T025925
CREATED:20230713T170909Z
LAST-MODIFIED:20231004T165011Z
UID:10000397-1697068800-1697155199@datascience.ucsd.edu
SUMMARY:HDSI Data Science Talent Day
DESCRIPTION:Data Science Talent Day is the annual recruiting event specifically dedicated to data science talent at UC San Diego. With well over 1000 students at the undergraduate and graduate level\, we are one of the largest data science academic programs in the country. The event is hosted by the Halıcıoğlu Data Science Institute and provides employers with a unique opportunity to meet\, network\, and recruit hundreds of our aspiring data scientists who are seeking internships and job opportunities. \nWe look forward to seeing you there! \nREGISTER HERE
URL:https://www.eventbrite.com/e/data-science-talent-day-tickets-642399112037?aff=oddtdtcreator
LOCATION:Price Center East Ballroom\, 9500 Gilman Drive\, La Jolla\, CA\, 92093\, United States
CATEGORIES:Industry
ATTACH;FMTTYPE=image/jpeg:https://datascience.ucsd.edu/wp-content/uploads/2023/10/Data-Science-Talent-Day-2023-Square.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20231016T130000
DTEND;TZID=America/Los_Angeles:20231016T140000
DTSTAMP:20260606T025925
CREATED:20231016T165002Z
LAST-MODIFIED:20231016T165640Z
UID:10000408-1697461200-1697464800@datascience.ucsd.edu
SUMMARY:In Silico: Simulators\, Emulators and the Human Brain Project
DESCRIPTION:Title: In Silico: Simulators\, Emulators and the Human Brain Project\n\n \nAbstract: The European Human Brain Project\, a flagship project of the European Union\, recently ended after 10 years of research and development. The goals of the HBP were to (1) explore the complexity of the human brain in space and time; (2) to transfer the knowledge broadly; (3) to provide research infrastructure for neuro-science; and (4) to create a community of researchers. One of the major challenges is to model neural activity\, from micro- to macro-scale\, in a way that enables simulation of the human brain. This leads to so-called in silico experiments\, which will be used “to validate models\, and to perform investigations that are not possible in the laboratory”. I will present examples of such experiments and discuss how they relate to\, and can benefit from\, statistical research on the design and analysis of computer experiments. My students and colleagues and I have been working on the potential advantages of replacing a slow/expensive simulator with a much faster and cheaper statistical emulator. Emulators are empirical replicas trained on data generated with the simulator. We have often used Gaussian process regression for this purpose\, but in some applications other methods (random forests\, polynomial regression) proved more effective. Emulators can be especially useful when the simulator runs are matched to data in the context of statistical inference. I will discuss the modeling options and present examples\, including simulation of neural basket cells\, calcium induced neural reactions\, and stochastic simulators like the Hodgkin-Huxley model.\n \nThis research has received funding from the European Union’s Horizon 2020 Framework Programme for Research and Innovation under the Specific Grant Agreement No. 785907 (Human Brain Project SGA2) and the Specific Grant Agreement No. 945539 (Human Brain Project SGA3). \n\n \nBio: Professor Steinberg received his PhD in Statistics in 1983 at the University of Wisconsin-Madison\, under the supervision of the legendary George Box. He has spent most of his academic career at Tel Aviv University\, while also being a consultant for many organizations and industries outside academia. He was elected Fellow of the American Statistical Association in 2008 and awarded the Gordon Chair for Probabilistic Mathematics in 2018. He works on a variety of topics in statistics\, industrial statistics and biostatistics\, including experimental design and smoothing methods.\n \n\nSpeaker: David Steinberg \n\nProfessor\, Department of Statistics and Operations Research \nSchool of Mathematical Sciences\nTel-Aviv University
URL:https://datascience.ucsd.edu/event/in-silico-simulators-emulators-and-the-human-brain-project/
LOCATION:3234 Matthews Ln\, La Jolla\, 92093\, United States
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20231016T150000
DTEND;TZID=America/Los_Angeles:20231016T160000
DTSTAMP:20260606T025925
CREATED:20231011T171113Z
LAST-MODIFIED:20231011T171113Z
UID:10000406-1697468400-1697472000@datascience.ucsd.edu
SUMMARY:IPE Data talk: Berk Ustun on Personalization and Worsenalization
DESCRIPTION:The Institute for Practical Ethics’ working group on Data Governance and Accountability (aka IPE Data) is thrilled to announce our first talk\, with UCSD’s very own Prof. Berk Ustun next Monday at 3pm\, on “When Personalization Harms Performance.” \nPlease also save the date Mon\, 11/13@3pm for a talk with Prof. Dan Ho from Stanford on assessing equity of algorithms in government services\, and be on the lookout for further talks we are scheduling in 2024 with some great scholars\, including Prof. Krystal Tsosie from ASU on indigenous data sovereignty. See the end for how to subscribe to our mailing list. \nDate: Mon\, Oct 16th at 3pm Pacific\nPlace: HDSI 123\, 1st floor multipurpose room and Zoom (https://ucsd.zoom.us/j/95047724642)\n*** note this is the new HDSI building next to Warren Lecture Hall\, not the old HDSI location in the San Diego Supercomputer Center building (UCSD maps\, Google maps pin\, enter from West / Warren Lecture Hall side)\nRSVP: https://forms.gle/yZQUkmtSrYNVBVCo9
URL:https://datascience.ucsd.edu/event/ipe-data-talk-berk-ustun-on-personalization-and-worsenalization/
LOCATION:3234 Matthews Ln\, La Jolla\, 92093\, United States
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20231017T140000
DTEND;TZID=America/Los_Angeles:20231017T150000
DTSTAMP:20260606T025925
CREATED:20231012T161810Z
LAST-MODIFIED:20231012T173716Z
UID:10000407-1697551200-1697554800@datascience.ucsd.edu
SUMMARY:Learning and Inference: a view from theoretical computer science |  Anindya De
DESCRIPTION:Title: “Learning and Inference: a view from theoretical computer science” \nAbstract: Machine learning and high-dimensional inference are a wellspring of fundamental algorithmic challenges in data science. In this talk\, I will discuss two strands of work in this line of research. \n(i) In the first part\, I will talk about “”estimation of fit”” type problems — the high level goal here is to understand how well the best model (from a class of models) fits the target data. My focus will be on “”sparse models””\, a standard assumption in machine learning to deal with data deficiency. In this setting\, we design algorithms for estimating fit where the complexity scales just in the sparsity parameter and is independent of the ambient dimension. \n(ii) In the second part\, I will discuss “”noisy reconstruction problems”” where the algorithm gets access to the target object through noisy samples. This formulation captures many well studied problems in machine learning. We give a new general algorithmic technique for such problems based on Fourier analysis which we refer to as “Fourier stability” and use this to design new\, state of the art algorithms for “”population recovery”” and “”trace reconstruction”” — two basic problems in unsupervised learning which have received significant attention in theoretical computer science. \nOur algorithms leverage methods and techniques from Boolean function analysis — a set of tools at the intersection of analysis and combinatorics — which has been very influential in complexity theory\, especially in areas like PCPs and hardness of approximation. Synergistically\, the development of this new algorithmic toolkit for problems in learning and inference has also led to discovery of results of intrinsic interest to probability theory and analysis\, some of which I will briefly survey.         \nBio: Anindya De is an Associate Professor of Computer Science at University of Pennsylvania. He finished his PhD from UC Berkeley in 2013 and was a postdoc at the Institute for Advanced Study\, Princeton and DIMACS\, Rutgers. He spent 3 years on the faculty at Northwestern University before moving to Penn in 2019. His main research interest is in Boolean function analysis and its applications in computational learning theory\, applied probability and more broadly\, theoretical computer science.     
URL:https://datascience.ucsd.edu/event/learning-and-inference-a-view-from-theoretical-computer-science-anindya-de/
LOCATION:3234 Matthews Ln\, La Jolla\, 92093\, United States
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20231030T130000
DTEND;TZID=America/Los_Angeles:20231030T140000
DTSTAMP:20260606T025925
CREATED:20231002T164053Z
LAST-MODIFIED:20231030T172523Z
UID:10000401-1698670800-1698674400@datascience.ucsd.edu
SUMMARY:The Uneasy Relation Between Deep Learning and Statistics
DESCRIPTION:Abstract: Deep learning uses the language and tools of statistics and classical machine learning\, including empirical and population losses and optimizing a hypothesis on a training set. But it uses these tools in regimes where they should not be applicable: the optimization task is non-convex\, models are often large enough to overfit\, and the training and deployment tasks can radically differ. In this talk I will survey the relation between deep learning and statistics. In particular we will discuss recent works supporting the emerging intuition that deep learning is closer in some aspects to human learning than to classical statistics. Rather than estimating quantities from samples\, deep neural nets develop broadly applicable representations and skills through their training.\n\nThe talk will not assume background knowledge in artificial intelligence or deep learning.\n\n\n \nBio: Boaz Barak is the Gordon McKay professor of Computer Science at Harvard University’s John A. Paulson School of Engineering and Applied Sciences. Barak’s research interests include all areas of theoretical computer science and in particular cryptography\, computational complexity\, and the foundations of machine learning. Previously\, he was a principal researcher at Microsoft Research New England\, and before that an associate professor (with tenure) at Princeton University’s computer science department. Barak has won the ACM dissertation award\, the Packard and Sloan fellowships\, and was also selected for Foreign Policy magazine’s list of 100 leading global thinkers for 2014. He was also chosen as a Simons investigator and a Fellow of the ACM. Barak is a member of the scientific advisory boards for Quanta Magazine and the Simons Institute for the Theory of Computing. He is also a board member of AddisCoder\, a non-profit organization for teaching algorithms and coding to high-school students in Ethiopia and Jamaica. Barak wrote with Sanjeev Arora the textbook “Computational Complexity: A Modern Approach”.
URL:https://datascience.ucsd.edu/event/the-uneasy-relation-between-deep-learning-and-statistics/
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/png:https://datascience.ucsd.edu/wp-content/uploads/2023/10/Encore-logo_HDSI-Website.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20231108T140000
DTEND;TZID=America/Los_Angeles:20231108T150000
DTSTAMP:20260606T025925
CREATED:20231106T182742Z
LAST-MODIFIED:20231106T182742Z
UID:10000409-1699452000-1699455600@datascience.ucsd.edu
SUMMARY:Adaptivity in Domain Adaptation and Friends | Samory Kpotufe
DESCRIPTION:Abstract: Domain adaptation\, transfer\, multitask\, meta\, few-shots\, or lifelong learning … these are all important recent directions in ML that all touch at the core of what we might mean by ‘AI’. As these directions all concern learning in heterogeneous and ever-changing environments\, they all share a central question: what information a ‘source’ distribution may have about a ‘target’ distribution\, or put differently\, which measures of discrepancy between distributions properly model such information.\nOur understanding of this central question is still rather fledgeling\, with both positive and negative results.\nOn one hand we show that traditional notions of distance and divergence between distributions (e.g.\, Wasserstein\, TV\, KL\, Renyi) are in fact too conservative: a source may be ‘far’ from a target under such traditional notions\, yet still admit much useful information about the target distribution. We then turn to the existence of ‘adaptive’ procedures\, i.e.\, procedures which can optimally leverage such information in the source data without any prior distributional knowledge. Here the picture is quite nuanced: while various existing approaches turn out to be adaptive in usual settings with a single source and hypothesis class\, no procedure can guarantee optimal rates adaptively in more general settings\, e.g.\, settings with multiple source datasets (as in multitask learning)\, or settings with multiple hypothesis classes (as in model selection or hyper-parameter tuning). \nSuch negative results raise new questions\, as they suggest that domain adaptation and related problems may benefit from more structure in practice than captured by current formalisms. \nThe talk is based on joint work with collaborators over the last few years\, namely\, G. Martinet\, S. Hanneke\, J. Suk\, Y. Mahdaviyeh\, N. Galbraith.
URL:https://datascience.ucsd.edu/event/adaptivity-in-domain-adaptation-and-friends-samory-kpotufe/
LOCATION:3234 Matthews Ln\, La Jolla\, 92093\, United States
END:VEVENT
END:VCALENDAR