Give us a call or drop by anytime, we endeavor to answer all inquiries within 24 hours.
PO Box 16122 Collins Street West Victoria, Australia
info@domain.com / example@domain.com
Phone: + (066) 0760 0260 / + (057) 0760 0560
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.
Instructors 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. To 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.
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.
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 […]
You're invited to join us in celebrating and socializing with HDSI alumni this summer when we gather for our annual celebration! Alumni are always eager to see their former professors, so if you happen to be in town, we would love to have you!
Causality is increasingly a part of AI, data science, robotics, and more, but it is not always clear how we can learn causality from data. This symposium will be featuring leading HDSI Faculty who will be providing an introductory overview on these methods, followed by domain-specific talks and open discussion.
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.
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 […]
TILOS Seminar: Towards Foundation Models for Graph Reasoning and AI 4 Science Michael Galkin, Research Scientist at AI Lab HDSI 123 and Zoom: https://ucsd.zoom.us/j/99334315002 Abstract: Foundation models in graph learning are […]
Recent advances in computing hardware (FPGAs, distributed parallel computing) and numerical methods (machine learning algorithms, automatic differentiation) create new possibilities for Fusion Power Plant optimization and control. In this talk, I will discuss some of the recent accomplishments of the Plasma Control Group at Princeton that take advantage of these new capabilities.