Large language models (LLMs)(Anil et al., 2023; Glaese et al., 2022; OpenAI, 2023; Ouyang
et al., 2022) have made remarkable strides in enhancing natural language understanding …

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 …

We address the issue of limit cycling behavior in training Generative Adversarial Networks
and propose the use of Optimistic Mirror Decent (OMD) for training Wasserstein GANs …

Potential games are arguably one of the most important and widely studied classes of
normal form games. They define the archetypal setting of multi-agent coordination as all …

The combination of deep reinforcement learning and search at both training and test time is
a powerful paradigm that has led to a number of successes in single-agent settings and …

Abstract We show that Optimistic Hedge--a common variant of multiplicative-weights-
updates with recency bias--attains ${\rm poly}(\log T) $ regret in multi-player general-sum …

Multi-agent reinforcement learning has made substantial empirical progresses in solving
games with a large number of players. However, theoretically, the best known sample …

Abstract Model-based reinforcement learning (RL), which finds an optimal policy using an
empirical model, has long been recognized as one of the cornerstones of RL. It is especially …

Online learning is a framework for the design and analysis of algorithms that build predictive
models by processing data one at the time. Besides being computationally efficient, online …

In this work, we study the computational complexity of reducing the squared gradient
magnitude for smooth minimax optimization problems. First, we present algorithms with …