Haipeng Luo

Haipeng Luo is an Associate Professor at the Thomas Lord Department of Computer Science, University of Southern California, holding the IBM Early Career Chair. He previously worked as a Postdoctoral Researcher at Microsoft Research, NYC, and has held visiting roles at Google and Amazon. His research focuses on developing practical machine learning algorithms with strong theoretical guarantees, particularly in online learning, bandit problems, reinforcement learning, and game theory.

• PhD in Computer Science, Princeton University (2011–2016)
• BSc in Computer Science, Peking University (2007–2011)

His work spans adversarial and stochastic environments, addressing challenges in reinforcement learning, game dynamics, calibration, and omniprediction. Recent publications highlight advancements in regret minimization, game equilibrium computation, and robust optimization frameworks. Key contributions include algorithms for zero-sum games, bandit problems with feedback graphs, and theoretical analyses of convergence properties in multi-agent systems.

Scientific accolades include Best Paper Awards at COLT 2021, COLT 2018, NeurIPS 2015, and ICML 2015. He has received prestigious grants such as the NSF CAREER Award (2020), Google Faculty Research Award (2020), and NSF CRII Award (2018). His students have secured academic and industry positions, and he actively teaches graduate courses in machine learning and online optimization.