conftrace_

loss landscape

202 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network optimization (45) neural network (28) gradient descent (27) sharpness-aware minimization (22) stochastic gradient descent (17) deep neural network (14) mode connectivity (13) flat minima (13) adversarial example (10) adversarial training (10)

Papers

On the Flatness of Loss Surface for Two-layered ReLU Networks ACML 2017 On the Quality of the Initial Basin in Overspecified Neural Networks ICML 2016