Related Past Activities

*All times in Pacific Time
|
Phase transitions in SGD beyond Lyapunov stability
Avrajit Ghosh (UC Berkeley)
View Details
|
Continuous Diffusion on the Hypercube: A Single Tilt–Mean Operator and Training-Free Reward Tilting
View Details
|
Hera: A Fast Optimization Algorithm for Softmax Self-attention
View Details
|
ML and AI Theory Seminar
View Details
|
Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization
Gabriel Clara (Simons Institute for the Theory of Computing)
View Details
|
Instance-wise Risk Comparisons in Linear Regression: Dominance and Admissibility
Jingfeng Wu (UC Berkeley)
View Details
–
Deep Learning Theory
View Details
|
CANCELLED: Optimal Online Learning Using Potential Functions
Yoav Freund (UC San Diego)
View Details
–
Deep Learning Theory Symposium
View Details Video