Login / Signup

When does SGD favor flat minima? A quantitative characterization via linear stability.

Lei WuMingze WangWeijie Su
Published in: CoRR (2022)
Keyphrases
  • quantitative and qualitative
  • data mining
  • linear systems
  • data sets
  • neural network
  • case study
  • multiscale
  • qualitative and quantitative