Tutorials


Mikhail Belkin

Theory of Deep Learning

Abstract

TBA

Biography

Mikhail Belkin is a Professor at Halicioglu Data Science Institute and Computer Science and Engineering Department at UCSD and an Amazon Scholar. Prior to that he was a Professor at the Department of Computer Science and Engineering and the Department of Statistics at the Ohio State University. He received his Ph.D. from the Department of Mathematics at the University of Chicago (advised by Partha Niyogi). His research interests are broadly in theory and applications of machine learning, deep 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 graph theory to data science. His more recent work has been concerned with understanding remarkable mathematical and statistical phenomena observed in deep learning. The empirical evidence necessitated revisiting some of the classical concepts in statistics and optimization, including the basic notion of over-fitting. One of his key findings has been the “double descent” risk curve that extends the textbook U-shaped bias-variance trade-off curve beyond the point of interpolation. His recent work focusses on understanding feature learning and over-parameterization in deep learning. Mikhail Belkin is an ACM Fellow and a recipient of a NSF Career Award and a number of best paper and other awards. He had served on the editorial boards of IEEE Proceedings on Pattern Analysis Machine Intelligence and the Journal of the Machine Learning Research. He is the editor-in-chief of SIAM Journal on Mathematics of Data Science (SIMODS).


Siva Theja Maguluri

Reinforcement Learning and Stochastic Approximation

Abstract

TBA

Biography

Prof. Siva Theja Maguluri is the Fouts Family Early Career Professor and an Associate Professor in the H. Milton Stewart School of Industrial & Systems Engineering at Georgia Tech. Before joining Georgia Tech, Prof. Maguluri spent two years in the Stochastic Processes and Optimization group within the Mathematical Sciences Department at the IBM T. J. Watson Research Center. He completed a Ph.D. in Electrical and Computer Engineering (ECE) from the University of Illinois at Urbana-Champaign (UIUC) in 2014, under the supervision of Prof. R. Srikant, following an MS in ECE also advised by Prof. Srikant and Prof. Bruce Hajek. Prof. Maguluri additionally holds an MS in Applied Mathematics from UIUC and a B.Tech in Electrical Engineering from the Indian Institute of Technology Madras. Prof. Maguluri has received several notable awards, including the NSF CAREER award in 2021, the 2017 Best Publication in Applied Probability Award from INFORMS Applied Probability Society, and second prize in the 2020 INFORMS Junior Faculty Interest Group (JFIG) Best Paper Competition. Joint research with his students received the Stephen S. Lavenberg Best Student Paper Award at IFIP Performance 2021. Recognized for teaching excellence, Prof. Maguluri received the Student Recognition of Excellence in Teaching: Class of 1934 CIOS Award in 2020 for ISyE 6761 and the CTL/BP Junior Faculty Teaching Excellence Award in 2020, presented by the Center for Teaching and Learning at Georgia Tech.


Prabha Mandayam

Quantum Information Theory and Quantum Error Correction

Abstract

TBA

Biography

Prof. Prabha Mandayam is an Associate Professor in the Department of Physics at the Indian Institute of Technology, Madras. Previously, she was an Inspire Faculty Fellow at the Chennai Mathematical Institute and a Postdoctoral Fellow with the Optics and Quantum Information Group at the Institute of Mathematical Sciences. She obtained her Ph.D. in Physics from the Institute for Quantum Information and Matter at Caltech under the supervision of John Preskill. Prof. Mandayam’s research interests lie in the field of quantum computing and quantum information theory. Specifically, she focuses on quantum error correction, the interplay between quantum foundations and quantum cryptography, and using quantum information as a tool to explore fundamental questions in theoretical physics.