Ruosong Wang

Ruosong Wang is an Assistant Professor in the Machine Learning Department within the School of Computer Science at Carnegie Mellon University. His research focuses on theoretical aspects of machine learning, particularly reinforcement learning, bandit problems, and algorithmic foundations.

Wang's research interests span several key areas in theoretical machine learning. He has made significant contributions to reinforcement learning theory, particularly in understanding sample complexity, horizon dependence, and function approximation. His work on bandit algorithms explores variance-aware and sparse linear settings, while his research on subspace embeddings contributes to fundamental algorithmic techniques. Wang's approach combines rigorous theoretical analysis with practical implications for learning algorithms.

His publication record shows a strong focus on theoretical guarantees and tight bounds for various learning problems. Wang's research demonstrates a progression from foundational algorithmic work to increasingly sophisticated analyses of reinforcement learning systems. His papers often address fundamental questions about the limits and possibilities of learning algorithms in complex environments.

Wang has published extensively at top-tier machine learning and theoretical computer science venues including ICML, NeurIPS, ICLR, and STOC. His collaborative work with leading researchers in the field demonstrates his integration into the theoretical machine learning community.

As an advisor and researcher, Wang contributes to advancing the theoretical foundations of machine learning, with particular emphasis on understanding the fundamental limits and possibilities of learning algorithms in sequential decision-making contexts.