Hisham Husain

Distributional Robustness with IPMs and links to Regularization and GANs

2020 · arXiv (Cornell University)

Robustness to adversarial attacks is an important concern due to the fragility of deep neural networks to small perturbations and has received an abundance of attention in recent years. Distributionally Robust Optimization (DRO), a particularly …

Regularized Policies are Reward Robust

2021 · arXiv (Cornell University)

Entropic regularization of policies in Reinforcement Learning (RL) is a commonly used heuristic to ensure that the learned policy explores the state-space sufficiently before overfitting to a local optimal policy. The primary motivation for using …