Presenter (offline): Hojung Jung (OSI Lab @KAIST AI)
Papers presented:
Implicit Gradient Regularization (Barrett et al., ICLR 2021)
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability (Cohen et al., ICLR 2021)
Stochastic Training is Not Necessary for Generalization (Geiping et al., ICLR 2022)
Presenter (offline): Minchan Jeong (OSI Lab @KAIST AI)
Presenter (online): Yujeong Lee (Samsung Research)
Slide and Paper
Presenter (offline): Hojung Jung (OSI Lab @KAIST AI)
Papers presented:
Three Factors Influencing Minima in SGD (Jastrzebski et al., ICANN 2018)
Power-Law Escape Rate of SGD (Mori et al., ICML 2022)