Stochastic optimization lies at the heart of machine learning, and its cornerstone is
stochastic gradient descent (SGD), a method introduced over 60 years ago. The last eight …

Stochastic nested optimization, including stochastic compositional, min-max, and bilevel
optimization, is gaining popularity in many machine learning applications. While the three …

Bilevel optimization have gained growing interests, with numerous applications found in
meta learning, minimax games, reinforcement learning, and nested composition …

Despite the success of single-agent reinforcement learning, multi-agent reinforcement
learning (MARL) remains challenging due to complex interactions between agents …

Areas under ROC (AUROC) and precision-recall curves (AUPRC) are common metrics for
evaluating classification performance for imbalanced problems. Compared with AUROC …

Policy evaluation is concerned with estimating the value function that predicts long-term
values of states under a given policy. It is a crucial step in many reinforcement-learning …

We study constrained nested stochastic optimization problems in which the objective
function is a composition of two smooth functions whose exact values and derivatives are …

Stochastic bilevel optimization generalizes the classic stochastic optimization from the
minimization of a single objective to the minimization of an objective function that depends …

Policy gradient (PG) gives rise to a rich class of reinforcement learning (RL) methods.
Recently, there has been an emerging trend to augment the existing PG methods such as …

Stochastic bilevel optimization generalizes the classic stochastic optimization from the
minimization of a single objective to the minimization of an objective function that depends …