Implicit learning dynamics in stackelberg games: Equilibria characterization, convergence analysis, and empirical study

T Fiez, B Chasnov, L Ratliff - International Conference on …, 2020 - proceedings.mlr.press
Contemporary work on learning in continuous games has commonly overlooked the
hierarchical decision-making structure present in machine learning problems formulated as …

Global convergence of policy gradient methods to (almost) locally optimal policies

K Zhang, A Koppel, H Zhu, T Basar - SIAM Journal on Control and …, 2020 - SIAM
Policy gradient (PG) methods have been one of the most essential ingredients of
reinforcement learning, with application in a variety of domains. In spite of the empirical …

The anisotropic noise in stochastic gradient descent: Its behavior of esca** from sharp minima and regularization effects

Z Zhu, J Wu, B Yu, L Wu, J Ma - ar** saddle points for effective generalization on class-imbalanced data
H Rangwani, SK Aithal… - Advances in Neural …, 2022 - proceedings.neurips.cc
Real-world datasets exhibit imbalances of varying types and degrees. Several techniques
based on re-weighting and margin adjustment of loss are often used to enhance the …