All talks listed in Pacific Time. Schedule subject to change.

–
Coffee and Check-In
–
Feature Learning: From Optimization to Modern Generalization

Margalit Glasgow (Simons Institute)
–
SDE Approximations and Scaling Rules for Distributed Deep Learning

Kaifeng Lyu (Simons Institute, UC Berkeley)
–
Quantum approach to classical optimization: why bother and what to do?

Jiaqi Leng (Simons Institute)
–
The dynamical view of machine learning: implicit biases of large learning rates

Yuqing Wang (UC Berkeley)
–
Distilling models using the linear representation hypothesis

Enric Boix (Simons Institute)
–
Break
–
Guiding machine design using insights from simple sandboxes

Bingbin Liu (Simons Institute)
–
Theoretical understanding of learning through the computational lens

Binghui Peng (Simons Institute, UC Berkeley)
–
Efficient Testable Agnostic Learning for Halfspaces

Arsen Vasilyan (UC Berkeley)
–
Towards Practical Algorithms for Outlier-Robust Estimation

Ankit Pensia (Simons Institute)
–
Data privacy and reliable learning

Lydia Zakynthinou (Simons Institute)