Mikhail Belkin » HDSI Team

HDSI Team

Leadership​

No results.

HDSI Team

NameTitleEmailPhone
Whitney GardenerFinancial & Faculty Assistantwadavis@ucsd.edu
Meredith LongoAcademic Advisor/Program Coordinatormlongo@ucsd.edu
858-534-5435
Vicente MalaveResearch Engineervmalave@ucsd.edu
Erik MjoenIndustry Relations Manageremjoen@ucsd.edu
Kyle Hofer-MoraAssistant Director of External Relations & Strategic Initiativekhofer@ucsd.edu
Jen MorganChief Admin. Officer/MSOjlmorgan@ucsd.edu
858-246-5425
Sonlong NguyenAsst. Student Affairs Manager and Academic Advisorsvn001@ucsd.edu

858-246-4619
Andrea PerezFund Manageranp058@ucsd.edu


Christian RoblesAcademic Advisorcgrobles@ucsd.edu858-534-0198
Sydney TranResearch Admin. for Sponsored Awards
Sophia TranIndustry Relations Specialist
Mona WangIntake Advisor858-534-0198
Logan WiedenhofferExecutive Assistantlwiedenhoffer@ucsd.edu



858-648-2932

Industry Relations

Mikhail Belkin

Professor
Website: misha.belkin-wang.org
Photo of Mikhail Belkin

Biographical Info

Mikhail Belkin received his Ph.D. in 2003 from the Department of Mathematics at the University of Chicago. His research interests are in theory and  applications of machine learning and data analysis. Some of his well-known work includes widely used Laplacian Eigenmaps, Graph Regularization and Manifold Regularization algorithms, which brought ideas from classical differential geometry and spectral analysis to data science. His recent work has been concerned with understanding remarkable mathematical and statistical phenomena observed in deep learning. This empirical evidence necessitated revisiting some of the basic concepts in statistics and optimization.  One of his key recent findings is the “double descent” risk curve that extends the textbook U-shaped bias-variance trade-off curve beyond the point of interpolation.

Mikhail Belkin is a recipient of a NSF Career Award and a number of best paper and other awards. He has served on the editorial boards of the Journal of Machine Learning Research, IEEE Pattern Analysis and Machine Intelligence and SIAM Journal on Mathematics of Data Science.

Post-Doctoral Fellow: Preetum Nakkiran

Student Affairs

No results.

Business Office

Mikhail Belkin

Professor
Website: misha.belkin-wang.org
Photo of Mikhail Belkin

Biographical Info

Mikhail Belkin received his Ph.D. in 2003 from the Department of Mathematics at the University of Chicago. His research interests are in theory and  applications of machine learning and data analysis. Some of his well-known work includes widely used Laplacian Eigenmaps, Graph Regularization and Manifold Regularization algorithms, which brought ideas from classical differential geometry and spectral analysis to data science. His recent work has been concerned with understanding remarkable mathematical and statistical phenomena observed in deep learning. This empirical evidence necessitated revisiting some of the basic concepts in statistics and optimization.  One of his key recent findings is the “double descent” risk curve that extends the textbook U-shaped bias-variance trade-off curve beyond the point of interpolation.

Mikhail Belkin is a recipient of a NSF Career Award and a number of best paper and other awards. He has served on the editorial boards of the Journal of Machine Learning Research, IEEE Pattern Analysis and Machine Intelligence and SIAM Journal on Mathematics of Data Science.

Post-Doctoral Fellow: Preetum Nakkiran

Communications

Mikhail Belkin

Professor
Website: misha.belkin-wang.org
Photo of Mikhail Belkin

Biographical Info

Mikhail Belkin received his Ph.D. in 2003 from the Department of Mathematics at the University of Chicago. His research interests are in theory and  applications of machine learning and data analysis. Some of his well-known work includes widely used Laplacian Eigenmaps, Graph Regularization and Manifold Regularization algorithms, which brought ideas from classical differential geometry and spectral analysis to data science. His recent work has been concerned with understanding remarkable mathematical and statistical phenomena observed in deep learning. This empirical evidence necessitated revisiting some of the basic concepts in statistics and optimization.  One of his key recent findings is the “double descent” risk curve that extends the textbook U-shaped bias-variance trade-off curve beyond the point of interpolation.

Mikhail Belkin is a recipient of a NSF Career Award and a number of best paper and other awards. He has served on the editorial boards of the Journal of Machine Learning Research, IEEE Pattern Analysis and Machine Intelligence and SIAM Journal on Mathematics of Data Science.

Post-Doctoral Fellow: Preetum Nakkiran