Andre Wibisono, PhD in Computer Science from the University of California, Berkeley. Joined Yale Faculty January 2021.

Assistant Professor

Address:

51 Prospect Street, New Haven, CT 06511

Bio:

Andre Wibisono’s research focuses on developing fast algorithms with robust guarantees for optimization and sampling problems, motivated by applications in machine learning and game theory. His research aims to develop a better theoretical understanding of fundamental problems in optimization, sampling, and game dynamics for machine learning and for the learning problem more generally. He received his bachelor’s degrees in Mathematics and Computer Science and his master’s degree in Computer Science from MIT. He received his master’s degree in Statistics and his PhD in Computer Science from the University of California, Berkeley. He has conducted postdoctoral research at the University of Wisconsin, Madison and Georgia Institute of Technology.

Representative Publications:
“Rapid convergence of the Unadjusted Langevin Algorithm: Isoperimetry suffices”, S. Vempala and A. Wibisono, Neural Information Processing Systems (NeurIPS), 2019.
“Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem”, A. Wibisono, Conference on Learning Theory (COLT), 2018.
“A variational perspective on accelerated methods in optimization”, A. Wibisono, A. Wilson, and M. Jordan, Proceedings of the National Academy of Sciences, 133, E7351–E7358, 2016.
“Minimax option pricing meets Black-Scholes in the limit”, J. Abernethy, R. Frongillo, and A. Wibisono. Symposium on the Theory of Computing (STOC), 2012.