Proposes Polyak schedulers for SAM with convergence proofs in deterministic and stochastic settings and empirical results showing reduced tuning needs.
Lightsam: Parameter-agnostic sharpness-aware mini- mization.arXiv preprint arXiv:2505.24399,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
Proposes Polyak schedulers for SAM with convergence proofs in deterministic and stochastic settings and empirical results showing reduced tuning needs.