The ODE Method for Stochastic Approximation and Reinforcement Learning with Markovian Noise

Optimizing Noise for f-Differential Privacy via Anti-Concentration and Stochastic Dominance

Expected Worst Case Regret via Stochastic Sequential Covering

We study the problem of sequential prediction and online minimax regret with stochastically generated features under a general loss function. In an online learning setting, Nature selects features...

Expected Worst Case Regret via Stochastic Sequential Covering

We study the problem of sequential prediction and online minimax regret with stochastically generated features under a general loss function. In an online learning setting, Nature selects features...