Area under the ROC curve, aka AUC, is a measure of choice for assessing the performance
of a classifier for imbalanced data. AUC maximization refers to a learning paradigm that …

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

Standard federated optimization methods successfully apply to stochastic problems with
single-level structure. However, many contemporary ML problems-including adversarial …

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

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

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

Bilevel optimization recently has received tremendous attention due to its great success in
solving important machine learning problems like meta learning, reinforcement learning …

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 …

In this paper, we consider non-convex stochastic bilevel optimization (SBO) problems that
have many applications in machine learning. Although numerous studies have proposed …

Stochastic compositional optimization generalizes classic (non-compositional) stochastic
optimization to the minimization of compositions of functions. Each composition may …