From Information Theory To Robust Bayesian Statistics

Yannick Baraud
University of Luxembourg

Andrew Barron
Yale University

Statistical Learning And Neural Nets

Peter Bartlett
University of California Berkeley
Google DeepMind

Joseph Chang
Yale University

Statistical Learning

David Donoho
Stanford University

Statistical Inference In The Wild

John Elder
Elder Research, Inc.

Addressing Large Models: Multiple And Hierarchical Universality

Meir Feder
Tel Aviv University
Tel-Aviv University

Tamar Gendler
Yale University

Banquet MC

Ed I. George
The Wharton School of the University of Pennsylvania

Probability Via Expectation Measures

Peter Harremoes
Copenhagen Business College

Sequential Goodness-of-fit Testing For Markov Chains

Tara Javidi
University of California at San Diego

Maximal Correlation And The Information-theoretic Central Limit Theorem

Oliver Johnson
University of Bristol

Complex Variables And The Central Limit Theorem

Iain Johnstone
Stanford University

On Greedy Algorithms For Local Statistical Learning Of Nonlinear Functions

Lee K. Jones
UMass Lowell
IPA

Sharp Convergence Rates For Matching Pursuit
Jason Klusowski
Princeton University

Information-theoretic Approaches To De Finetti-style Theorems

Ioannis Kontoyiannis
University of Cambridge

Abstraction In Minds And Machines

John Lafferty
Yale University
Wu Tsai Institute

Old And New Vignettes In The World Of Entropy Power Inequalities

Mokshay Madiman
University of Delaware

Solving Overparametrized Systems Of Nonlinear Equations

Andrea Montanari
Stanford University

Network Comparison Via Optimal Transport

Andrew Nobel
University of North Carolina at Chapel Hill

Andrew: The Illinois Years

Vince Poor
Princeton University

Structure And Randomness In Function Approximation, The Barron Way

Max Raginsky
University of Illinois at Urbana-Champaign

Minimax Optimal Bayes Mixtures For Memoryless Sources Over Large Alphabets

Teemu Roos
University of Helsinki

Six Years Of Information Theory, Probability, And Statistical Learning: What It's Like To Be A Student Of Andrew Barron

Cynthia Rush
Columbia University

Robust Inference For Functional Data

Douglas Simpson
University of Illinois Urbana-Champaign

Tight Risk Bound Of MDL Estimators For Simple ReLU Neural Networks

Jun'ichi Takeuchi
Kyushu University

Multi-view Models And Adaptive Density Estimation Under Low-rank Constraints

Alexandre Tsybakov
CREST-ENSAE Paris

Barron-type Density And Distribution Esimation Consistent In Information And Related Divergences

Edward van der Meulen
KU Leuvan

Linear Methods For Nonlinear Inverse Problems.

Aad van der Vaart
Delft University of Technology

Sparse Superposition Coding And Communication Over Many-User Channels

Ramji Venkataramanan
University of Cambridge

Learning Low-rank Functions With Neural Networks

Rebecca Willett
University of Chicago