206 citations · 808 across the 40 of their papers we have counts for
7 papers · 1 filter
Malign Overfitting: Interpolation Can Provably Preclude Invariance
Yoav Wald, Gal Yona, Uri Shalit +1
Learned classifiers should often possess certain invariance properties meant to encourage fairness, robustness, or out-of-distribution generalization. However, multiple recent work…
RECAPP: Crafting a More Efficient Catalyst for Convex Optimization
Yair Carmon, Arun Jambulapati, Yujia Jin +1
The accelerated proximal point algorithm (APPA), also known as "Catalyst", is a well-established reduction from convex optimization to approximate proximal point computation (i.e.,…
Optimal and Adaptive Monteiro-Svaiter Acceleration
Yair Carmon, Danielle Hausler, Arun Jambulapati +2
We develop a variant of the Monteiro-Svaiter (MS) acceleration framework that removes the need to solve an expensive implicit equation at every iteration. Consequently, for any $p\…
Making SGD Parameter-Free
Yair Carmon, Oliver Hinder
We develop an algorithm for parameter-free stochastic convex optimization (SCO) whose rate of convergence is only a double-logarithmic factor larger than the optimal rate for the c…
Distributionally Robust Optimization via Ball Oracle Acceleration
Yair Carmon, Danielle Hausler
We develop and analyze algorithms for distributionally robust optimization (DRO) of convex losses. In particular, we consider group-structured and bounded -divergence uncertaint…
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre +8
The conventional recipe for maximizing model accuracy is to (1) train multiple models with various hyperparameters and (2) pick the individual model which performs best on a held-o…