image:wibisono
      Andre Wibisono

YALE UNIVERSITY

andre.wibisono [at] yale [dot] edu

I am an assistant professor in the Department of Computer Science at Yale University, with a secondary appointment in the Department of Statistics & Data Science. My research interests are in the design and analysis of algorithms for machine learning, in particular for problems in optimization, sampling, and game theory.

I received my BS degrees in Mathematics and in Computer Science from MIT. I received my MEng in Computer Science from MIT, advised by Tomaso Poggio. I received by MA in Statistics from UC Berkeley, and my PhD in Computer Science from UC Berkeley, advised by Michael I. Jordan. Before joining Yale in 2021, I have done postdoctoral research at the University of Wisconsin-Madison, working with Po-Ling Loh and Varun Jog, and at the Georgia Institute of Technology, working with Jacob Abernethy and Santosh Vempala.


TEACHING

• CPSC 486/586: Probabilistic Machine Learning (Spring 2023-2026)
• CPSC/ECON 365: Algorithms (Fall 2023-2024, Fall 2026, Spring 2022)
• CPSC 481/581: Introduction to Machine Learning (Fall 2021)
• CPSC 661: Sampling Algorithms in Machine Learning (Spring 2021)


RESEARCH GROUP

• Siddharth Mitra
• Kaylee (Yingxi) Yang
• Jane H. Lee
• Qiang Fu
• Peter (Xiuyuan) Wang

RESEARCH ALUMNI

• Jun-Kun Wang (postdoc 2021-2023, now at UCSD)
• Jiaming Liang (postdoc 2022-2023, now at University of Rochester)


RESEARCH

For complete publication list, please see Google Scholar

• Accelerated Mixing Time of Randomized Hamiltonian Monte Carlo
Siddharth Mitra, Vishwak Srinivasan, Xiuyuan Wang, Andre Wibisono
arXiv:2607.12902
• Accelerated convex optimization via Hamiltonian dynamics with deterministic integration time
Xiuyuan Wang, Vishwak Srinivasan, Qiang Fu, Siddharth Mitra, Ashia Wilson, Andre Wibisono
COLT (Conference on Learning Theory) 2026
• The geometry of efficient nonconvex sampling
Santosh Vempala, Andre Wibisono
COLT (Conference on Learning Theory) 2026
• When and why is optimistic multiplicative weights slow? The geometry of energy dissipation
John Lazarsfeld, Anas Barakat, Georgios Piliouras, Antonios Varvitsiotis, Andre Wibisono
arXiv:2605.13242
• Tail-sensitive KL and Renyi convergence of unadjusted Hamiltonian Monte Carlo via one-shot couplings
Nawaf Bou-Rabee, Siddharth Mitra, Andre Wibisono
arXiv:2601.09019
• A symplectic analysis of alternating mirror descent
Jonas Katona, Xiuyuan Wang, Andre Wibisono
JMLR (Journal of Machine Learning Research), 27(44):1--61, 2026
• Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality
Andre Wibisono
IEEE Transactions on Information Theory, 72(5):2667--2688, 2026 [IEEE-IT version]
Extended abstract presented at COLT (Conference on Learning Theory) 2025
• Characterizing Dependence of Samples along the Langevin Dynamics and Algorithms via Contraction of Phi-Mutual Information
Jiaming Liang, Siddharth Mitra, Andre Wibisono
IEEE Transactions on Information Theory, 72(2):921--945, 2026 [IEEE-IT version]
Extended abstract presented at COLT (Conference on Learning Theory) 2025
• Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time
Qiang Fu Andre Wibisono
NeurIPS (Neural Information Processing Systems) 2025, Spotlight
• Fast and Furious Symmetric Learning in Zero-Sum Games: Gradient Descent as Fictitious Play
John Lazarsfeld, Georgios Piliouras, Ryann Sim, Andre Wibisono
COLT (Conference on Learning Theory) 2025
• On the Convergence of Min-Max Langevin Dynamics and Algorithm
Yang Cai, Siddharth Mitra, Xiuyuan Wang, Andre Wibisono
COLT (Conference on Learning Theory) 2025
• High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin Algorithm
Vishwak Srinivasan, Andre Wibisono, Ashia Wilson
ALT (Algorithmic Learning Theory) 2025
• Fast Convergence of Phi-Divergence Along the Unadjusted Langevin Algorithm and Proximal Sampler
Siddharth Mitra, Andre Wibisono
ALT (Algorithmic Learning Theory) 2025
• Optimal score estimation via empirical Bayes smoothing
Andre Wibisono, Yihong Wu, Kaylee Yingxi Yang
COLT (Conference on Learning Theory) 2024
• Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin Algorithm
Vishwak Srinivasan, Andre Wibisono, Ashia Wilson
COLT (Conference on Learning Theory) 2024
• Extragradient Type Methods for Riemannian Variational Inequality Problems
Zihao Hu, Guanghui Wang, Xi Wang, Andre Wibisono, Jacob Abernethy, Molei Tao
AISTATS (Artificial Intelligence and Statistics) 2024
• Learning Exponential Families from Truncated Samples
Jane Lee, Andre Wibisono, Manolis Zampetakis
NeurIPS (Neural Information Processing Systems) 2023
• On a Class of Gibbs Sampling over Networks
Bo Yuan, Jiaojiao Fan, Jiaming Liang, Andre Wibisono, Yongxin Chen
COLT (Conference on Learning Theory) 2023
• Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation
Jun-Kun Wang, Andre Wibisono
ICLR (International Conference on Learning Representations) 2023
• Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time
Jun-Kun Wang, Andre Wibisono
ICLR (International Conference on Learning Representations) 2023
• Continuized Acceleration for Quasar Convex Functions in Non-Convex Optimization
Jun-Kun Wang, Andre Wibisono
ICLR (International Conference on Learning Representations) 2023
• Convergence in KL Divergence of the Inexact Langevin Algorithm with Application to Score-based Generative Models
Kaylee Yingxi Yang, Andre Wibisono
arXiv preprint arXiv:2211.01512, 2022
• Alternating Mirror Descent for Constrained Min-Max Games
Andre Wibisono, Molei Tao, Georgios Piliouras
NeurIPS (Neural Information Processing Systems) 2022
• Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out
Jun-Kun Wang, Chi-Heng Lin, Andre Wibisono, Bin Hu
ICML (International Conference on Machine Learning) 2022
• Improved analysis for a proximal algorithm for sampling
Yongxin Chen, Sinho Chewi, Adil Salim, Andre Wibisono
COLT (Conference on Learning Theory) 2022
• The Mirror Langevin Algorithm Converges with Vanishing Bias
Ruilin Li, Molei Tao, Santosh S. Vempala, Andre Wibisono
ALT (Algorithmic Learning Theory) 2022
• Last-iterate convergence rates for min-max optimization
Jacob Abernethy, Kevin Lai, and Andre Wibisono
ALT (Algorithmic Learning Theory) 2021
• Fast Convergence of Fictitious Play for Diagonal Payoff Matrices
Jacob Abernethy, Kevin Lai, and Andre Wibisono
SODA (Symposium on Discrete Algorithms) 2021
• Proximal Langevin Algorithm: Rapid convergence under isoperimetry
Andre Wibisono
arXiv preprint arXiv:1911.01469, 2019
• Rapid convergence of the Unadjusted Langevin Algorithm: Isoperimetry suffices
Santosh Vempala and Andre Wibisono
NeurIPS (Neural Information Processing System) 2019
arXiv version | poster | expanded journal version in GAFA 2023
• Accelerating Rescaled Gradient Descent: Fast optimization of smooth functions
Ashia Wilson, Lester Mackey, and Andre Wibisono
NeurIPS (Neural Information Processing System) 2019
• Convexity of mutual information along the Ornstein-Uhlenbeck flow
Andre Wibisono and Varun Jog
ISITA (International Symposium on Information Theory and Applications) 2018
• Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem
Andre Wibisono
COLT (Conference on Learning Theory) 2018
• Convexity of mutual information along the heat flow
Andre Wibisono and Varun Jog
ISIT (International Symposium on Information Theory) 2018
• Information and estimation in Fokker-Planck channels
Andre Wibisono, Varun Jog, and Po-Ling Loh
ISIT (International Symposium on Information Theory) 2017
• A variational perspective on accelerated methods in optimization
Andre Wibisono, Ashia Wilson, and Michael Jordan
Proceedings of the National Academy of Sciences, 133, E7351--E7358, 2016. [arXiv version]
• Optimal rates for zero-order convex optimization: the power of two function evaluations
John Duchi, Michael Jordan, Martin Wainwright, and Andre Wibisono
IEEE Transactions on Information Theory, 61(5): 2788--2806, May 2015
• A Hadamard-type lower bound for symmetric diagonally dominant positive matrices
Christopher Hillar and Andre Wibisono
Linear Algebra and Applications, 472: 135--141, 2015
• Convexity of reweighted Kikuchi approximation
Po-Ling Loh and Andre Wibisono
NIPS (Neural Information Processing System) 2014
• How to hedge an option against an adversary: Black-Scholes pricing is minimax optimal
Jake Abernethy, Peter Bartlett, Rafael Frongillo, and Andre Wibisono
NIPS (Neural Information Processing System) 2013
• Streaming variational Bayes
Tamara Broderick, Nicholas Boyd, Andre Wibisono, Ashia Wilson, and Michael Jordan
NIPS (Neural Information Processing System) 2013
• Maximum entropy distributions on graphs
Christopher Hillar and Andre Wibisono
arXiv preprint arXiv:1301.3321, 2013
• Inverses of symmetric, diagonally dominant positive matrices and applications
Christopher Hillar, Shaowei Lin, and Andre Wibisono
arXiv preprint arXiv:1203.6812, 2013
• Finite sample convergence rates of zero-order stochastic optimization methods
John Duchi, Michael Jordan, Martin Wainwright, and Andre Wibisono
NIPS (Neural Information Processing System) 2012
• Minimax option pricing meets Black-Scholes in the limit
Jacob Abernethy, Rafael Frongillo, and Andre Wibisono
STOC (Symposium on the Theory of Computing) 2012

THESES

• Variational and Dynamical Perspectives on Learning and Optimization
PhD in Computer Science, University of California, Berkeley, May 2016
• Maximum Entropy Distributions on Graphs
MA in Statistics, University of California, Berkeley, May 2013
• Generalization and Properties of the Neural Response
MEng in Computer Science, Massachusetts Institute of Technology, June 2010