Zhuoran Yang, PhD

Zhuoran Yang's research explores the theoretical and algorithmic foundations of machine learning, statistics, and optimization, with a focus on their applications in large-scale and multi-agent decision-making problems. His work emphasizes understanding the emergent behaviors of large language models during pre-training and post-training, uncovering their inner mechanisms, and leveraging these insights for decision-making tasks. Additionally, he is dedicated to developing efficient multi-agent learning algorithms for strategic environments where agents interact with varying objectives, including human interactions. By combining deep theoretical insights with practical algorithms, his research aims to push the boundaries of artificial intelligence and reinforcement learning for complex, real-world challenges​.

deep learning ;  neural networks ;  optimization ;  statistical methods ;  language models  

algorithms ;  artificial intelligence ;  decision-making ;  machine learning  

Yang is an Assistant Professor of Statistics and Data Science at Yale University. His research lies at the intersection of machine learning, statistics, game theory, and optimization, with a focus on the foundations of reinforcement learning in multi-agent systems and the emergent behaviors of large language models during pre-training and post-training. Prior to Yale, he was a postdoctoral researcher at UC Berkeley under Michael I. Jordan, earned his PhD in Operations Research and Financial Engineering from Princeton University under Jianqing Fan and Han Liu, and completed his BS in Mathematics at Tsinghua University.