Skip to content
conftrace_

flat region

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network optimization (2) scale transformation (1) multi-layer neural network (1) sharp local minimum (1) stochastic optimizer (1) gaussian input (1) descent direction (1) large batch training (1) neural network (1) loss surface (1)

Papers

Concurrent Adversarial Learning for Large-Batch Training ICLR 2022 On the Flatness of Loss Surface for Two-layered ReLU Networks ACML 2017 An analysis on negative curvature induced by singularity in multi-layer neural-network learning NeurIPS 2010