LE-SAM inverts SAM by fixing the loss budget instead of the parameter-space radius, yielding better generalization across benchmarks.
arXiv preprint arXiv:2406.04142 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
fields
cs.LG 3verdicts
UNVERDICTED 3representative citing papers
Polyak-style step sizes for Schedule-Free SGD and Adam achieve O(1/sqrt(t)) anytime last-iterate rates for convex Lipschitz problems using per-iteration loss and gradient information.
Presents a model-based proximal framework for adaptive momentum in first-order optimizers by using a two-plane approximation of the objective to dynamically set the memory coefficient online.
citing papers explorer
-
Fix the Loss, Not the Radius: Rethinking the Adversarial Perturbation of Sharpness-Aware Minimization
LE-SAM inverts SAM by fixing the loss budget instead of the parameter-space radius, yielding better generalization across benchmarks.
-
Taking the Road Less Scheduled with Adaptive Polyak Steps
Polyak-style step sizes for Schedule-Free SGD and Adam achieve O(1/sqrt(t)) anytime last-iterate rates for convex Lipschitz problems using per-iteration loss and gradient information.
-
Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization
Presents a model-based proximal framework for adaptive momentum in first-order optimizers by using a two-plane approximation of the objective to dynamically set the memory coefficient online.