conftrace_

wide minima

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

convex quadratic (1) hessian spectral norm (1) neural network generalization (1) deep network (1) learning rate schedule (1) sharpness-aware minimization (1) gradient-based optimization (1)

Papers

The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima JMLR 2023 Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule JMLR 2023