This article surveys reinforcement learning from the perspective of optimization and control,
with a focus on continuous control applications. It reviews the general formulation …

Zeroth-order (ZO) optimization is a subset of gradient-free optimization that emerges in many
signal processing and machine learning (ML) applications. It is used for solving optimization …

Fine-tuning language models (LMs) has yielded success on diverse downstream tasks, but
as LMs grow in size, backpropagation requires a prohibitively large amount of memory …

This monograph portrays optimization as a process. In many practical applications the
environment is so complex that it is infeasible to lay out a comprehensive theoretical model …

The goal of a decision-based adversarial attack on a trained model is to generate
adversarial examples based solely on observing output labels returned by the targeted …

Multi-armed bandit problems are the most basic examples of sequential decision problems
with an exploration-exploitation trade-off. This is the balance between staying with the option …

Multi-armed bandits a simple but very powerful framework for algorithms that make
decisions over time under uncertainty. An enormous body of work has accumulated over the …

Online learning is a well established learning paradigm which has both theoretical and
practical appeals. The goal of online learning is to make a sequence of accurate predictions …

A fundamental challenge in interactive learning and decision making, ranging from bandit
problems to reinforcement learning, is to provide sample-efficient, adaptive learning …

Convex empirical risk minimization is a basic tool in machine learning and statistics. We
provide new algorithms and matching lower bounds for differentially private convex …