Theoretical Foundations: From the Early Days of Neural Networks to the Modern Deep Learning Era

Location

Calvin Lab auditorium

Date

Thursday, Apr. 9 – Friday, Apr. 10, 2026

About

This workshop celebrates Professor Peter Bartlett's 60th birthday. From his pioneering research on the generalization ability of neural networks in the 1990s to his recent efforts to rigorously understand phenomena such as benign overfitting in deep learning, Peter has been at the forefront of theoretical developments in machine learning for over three decades. As associate director of the Simons Institute from 2017 to 2022, he facilitated numerous workshops that advanced foundational work in areas such as data science, deep learning, machine learning, reinforcement learning, and statistical inference. This workshop brings together both established researchers and emerging leaders to reflect on the past achievements of machine learning theory and to help shape its future.

Chairs/Organizers

Jacob Abernethy

(Georgia Institute of Technology)

Alekh Agarwal

(Google)

Saptarshi Chakraborty

(University of Michigan)

Sasha Rakhlin

(MIT)

Ambuj Tewari

(University of Michigan)

Invited Participants

Ishaq Aden-Ali (Berkeley), Alekh Agarwal (Google), Misha Belkin (UC San Diego), Shai Ben-David (University of Waterloo), Kush Bhatia (Google DeepMind), Peter Bickel (UC Berkeley), Florentina Bunea (Cornell University), Saptarshi Chakraborty (University of Michigan), Niladri Chatterji (OpenAI), Xiang Cheng (Duke University), Yeshwanth Cherapanamjeri (Nanyang Technological University), Inderjit Dhillon (Google), Peng Ding (University of California, Berkeley), Spencer Frei (Google DeepMind), Rafael Frongillo (University of Colorado Boulder), Gautam Goel (Simons Institute, UC Berkeley), Shafi Goldwasser (Simons Institute), Arthur Gretton (University College London (UCL)), Steffen Grünewälder (University of York), Nika Haghtalab (UC Berkeley), Elad Hazan (Princeton University), Azadeh Khaleghi (ENSAE, CREST), Jason Lee (Princeton University), Myrto Limnios (Ecole Polytechnique Federale de Lausanne, Mathematics Section), Licong Lin (UC Berkeley), Michael Lindsey (UC Berkeley), David Lovell (QUT, Australia), Yian Ma (UCSD), Alan Malek (DeepMind), Jon McAuliffe (UC Berkeley), Song Mei (UC Berkeley), Shahar Mendelson (Texas A&M University), Wenlong Mou (University of Toronto), Andrew Nobel (University of North Carolina, Chapel Hill), Aldo Pacchiano (Boston University), Alexander Rakhlin (MIT), Tselil Schramm (Stanford University), Alex Smola (Boson AI), Nathan Srebro (Toyota Technological Institute at Chicago), Matus Telgarsky (Courant Institute, NYU), Ambuj Tewari (University of Michigan), Ryan Tibshirani (University of California, Berkeley), Umesh Vazirani (Simons Institute, UC Berkeley), Roman Vershynin (UC Irvine), Yusu Wang (UCSD), Manfred Warmuth (Google), Marten Wegkamp (Cornell University), Susan Wei (Monash Univeristy), Stephen Wright (University of Wisconsin-Madison), Jingfeng Wu (UC Berkeley), Bin Yu (UC Berkeley), Austin Zane (UC Berkeley), Nikita Zhivotovskiy (UC Berkeley)

Registration is required for in-person attendance, access to the livestream, and early access to the recording. Space may be limited, and you are advised to register early.

For additional information please visit: https://simons.berkeley.edu/participating-workshop.

Please note: the Simons Institute regularly captures photos and video of activity around the Institute for use in videos, publications, and promotional materials.