Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions
Bingxu Liu, Jiashun Liu, Johan Obando-Ceron +5
While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stat…
cs.LG2026
Rethinking Bregman Divergences in Kronecker-Factored Optimizers
Bing Liu, Wenjie Zhou, Chengcheng Zhao
Shampoo-style optimizers approximate gradient covariance matrices using Kronecker-factored structures. Recent work~\cite{lin2026understanding} showed that such approximations can b…