Bio:
Sham Kakade is a Gordon McKay Professor of Computer Science and Statistics at Harvard University and co-director of the Kempner Institute. He advances both the theory and practice of AI and deep learning. His thesis established core statistical foundations of reinforcement learning, and his subsequent work developed the first provably efficient policy search methods and mathematical foundations for sequential decision making. His contributions to ML and AI include scalable training methods for large language models and foundation models, tensor methods for latent variable estimation, and foundational theory for deep learning (feature learning, memorization, emergence). He is the recipient of the ICML Test of Time Award (2020) and the INFORMS Revenue Management and Pricing Prize (2014).
Sham completed his undergraduate studies in physics at Caltech working with John Preskill in quantum computing, followed by a Ph.D. in computational neuroscience at the Gatsby Unit, UCL, under Peter Dayan. After a postdoc at UPenn working with Michael Kearns, he held positions at the University of Washington, Microsoft Research New England, the Wharton School, and the Toyota Technological Institute at Chicago.