About

I am an Assistant Professor at Princeton ORFE. My research interests are broadly at the interface of optimization, probability, and machine learning, with a focus on the design and analysis of efficient algorithms.

Previously, I received my undergrad degree from Princeton, my PhD in Electrical Engineering and Computer Science from MIT, and was an assistant professor at UPenn where I created the UPenn Optimization Seminar and the FOLDS seminar. I am interested in practical implementations as well as theory, and have spent time in both tech (Apple Research, Google Research) and Wall Street (DE Shaw, Tower Research).

In my free time, I like to ski, play tennis, and eat too many cookies. I also like chess and, in a past life, I obtained an International Master norm in Spain. In another past life I swam on the Oxford varsity team.

Publications

Preprints

• Min-Max Optimization Is Strictly Easier Than Variational Inequalities
  Henry Shugart, Jason Altschuler.
  Preprint, 2025.
  

• Negative Stepsizes Make Gradient-Descent-Ascent Converge
  Henry Shugart, Jason Altschuler.
  Preprint, 2025.
  

• Algorithmic warm starts for Hamiltonian Monte Carlo
  Matthew Zhang, Jason Altschuler, Sinho Chewi.
  Preprint, 2026.
  

• Shifted Composition IV: Toward Ballistic Acceleration for Log-Concave Sampling
  Jason Altschuler, Sinho Chewi, Matthew Zhang.
  STOC 2026, to appear.
  

Expository writing

• Stepsize Hedging: an Alternative Mechanism for Accelerating Gradient Descent
  Jason Altschuler, Pablo Parrilo
  INFORMS Computing Society Newsletter, invited Research Highlight, 2026.
  

• Flows, Scaling, and Entropy Revisited: a Unified Perspective via Optimizing Joint Distributions
  Jason Altschuler
  SIAM Group on Optimization's Views and News, invited article, 2022.
  

Journal articles

• Optimized Methods for Composite Optimization: a Reduction Perspective
  Jinho Bok, Jason Altschuler.
  Mathematical Programming, 2026. (Preliminary conference version in COLT)
  

• Near-Linear Runtime for a Classical Matrix Preconditioning Algorithm
  Xufeng Cai, Jason Altschuler, Jelena Diakonikolas.
  Journal of the ACM, 2026.
  

• Acceleration by Random Stepsizes: Hedging, Equalization, and the Arcsine Stepsize Schedule
  Jason Altschuler, Pablo Parrilo.
  Foundations of Computational Mathematics, to appear in 2026+.
  

• Shifted Composition III: Local Error Framework for KL Divergence
  Jason Altschuler, Sinho Chewi.
  Foundations of Computational Mathematics, to appear in 2026+.
  

• Shifted Composition II: Shift Harnack Inequalities and Curvature Upper Bounds
  Jason Altschuler, Sinho Chewi.
  IEEE Transactions on Information Theory, 2025.
  

• Shifted Composition I: Harnack and Reverse Transport Inequalities
  Jason Altschuler, Sinho Chewi.
  IEEE Transactions on Information Theory, 2025.
  

• Resolving the mixing time of the Langevin Algorithm to its stationary distribution for log-concave sampling
  Jason Altschuler, Kunal Talwar.
  SIAM Journal on Mathematics of Data Science, 2025. (Preliminary conference version in COLT)
  

• Acceleration by Stepsize Hedging: Silver Stepsize Schedule for Smooth Convex Optimization
  Jason Altschuler, Pablo Parrilo.
  Mathematical Programming, 2024.
  INFORMS Computing Society Prize 1/2
  

• Acceleration by Stepsize Hedging: Multi-Step Descent and the Silver Stepsize Schedule
  Jason Altschuler, Pablo Parrilo.
  Journal of the ACM, 2024.
  INFORMS Computing Society Prize 2/2
  

• Faster high-accuracy log-concave sampling via algorithmic warm starts
  Jason Altschuler, Sinho Chewi.
  Journal of the ACM, 2024. (Preliminary conference version in FOCS)
  

• On the Privacy of Noisy Stochastic Gradient Descent for Convex Optimization
  Jason Altschuler, Jinho Bok, Kunal Talwar.
  SIAM Journal on Computing, 2024. (Preliminary conference version in NeurIPS oral)
  

• Kernel approximation on algebraic varieties
  Jason Altschuler, Pablo Parrilo.
  SIAM Journal on Applied Algebra and Geometry, 2023.
  

• Polynomial-time algorithms for Multimarginal Optimal Transport problems with structure
  Jason Altschuler, Enric Boix-Adsera.
  Mathematical Programming, 2023.
  

• Asymptotics for semi-discrete entropic optimal transport
  Jason Altschuler, Jonathan Niles-Weed, Austin Stromme.
  SIAM Journal on Mathematical Analysis, 2022.
  

• Near-linear convergence of the Random Osborne algorithm for Matrix Balancing
  Jason Altschuler, Pablo Parrilo.
  Mathematical Programming, 2023.
  

• Approximating Min-Mean-Cycle for low-diameter graphs in near-optimal time and memory
  Jason Altschuler, Pablo Parrilo.
  SIAM Journal on Optimization, 2022.
  

• Wasserstein barycenters are NP-hard to compute
  Jason Altschuler, Enric Boix-Adsera.
  SIAM Journal on Mathematics of Data Science, 2022.
  

• Wasserstein barycenters can be computed in polynomial time in fixed dimension [poster, slides]
  Jason Altschuler, Enric Boix-Adsera.
  Journal of Machine Learning Research, 2021.
  

• Hardness results for Multimarginal Optimal Transport problems
  Jason Altschuler, Enric Boix-Adsera.
  Discrete Optimization, 2021.
  

• Online learning over a finite action set with limited switching [poster, talk]
  Jason Altschuler, Kunal Talwar.
  Mathematics of Operations Research, 2021. (Preliminary conference version in COLT)

• Lyapunov Exponent of Rank One Matrices: Ergodic Formula and Inapproximability of the Optimal Distribution [slides]
  Jason Altschuler, Pablo Parrilo.
  SIAM Journal on Control and Optimization, 2020. (Preliminary conference version in CDC)

• Best arm identification for contaminated bandits
  Jason Altschuler, Victor-Emmanuel Brunel, Alan Malek.
  Journal of Machine Learning Research, 2019.

• Inclusion of forbidden minors in random representable matroids
  Jason Altschuler, Elizabeth Yang.
  Discrete Mathematics, 2017.

Conference proceedings

• Accelerating proximal gradient descent via silver stepsizes
  Jinho Bok, Jason Altschuler.
  COLT 2025, to appear.
  

• Shifted Interpolation for Differential Privacy
  Jinho Bok, Weijie Su, Jason Altschuler.
  ICML 2024.
  

• Faster high-accuracy log-concave sampling via algorithmic warm starts
  Jason Altschuler, Sinho Chewi.
  FOCS 2023.
  

• Privacy of Noisy Stochastic Gradient Descent: more iterations without more privacy loss
  Jason Altschuler, Kunal Talwar.
  NeurIPS 2022. (Selected for oral presentation)
  

• Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent
  Jason Altschuler, Sinho Chewi, Patrik Gerber, Austin Stromme.
  NeurIPS 2021. (Selected for spotlight presentation)
  

• Lyapunov Exponent of Rank One Matrices: Ergodic Formula and Inapproximability of the Optimal Distribution [slides]
  Jason Altschuler, Pablo Parrilo.
  CDC 2019.

• Massively scalable Sinkhorn distances via the Nyström method
  Jason Altschuler, Francis Bach, Alessandro Rudi, Jonathan Niles-Weed.
  NeurIPS 2019.
  

• Online learning over a finite action set with limited switching [poster, talk]
  Jason Altschuler, Kunal Talwar.
  COLT 2018.

• Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration [poster]
  Jason Altschuler, Jonathan Weed, Philippe Rigollet.
  NeurIPS 2017. (Selected for spotlight presentation)
  

• Greedy column subset selection: new bounds and distributed algorithms [poster, slides]
  Jason Altschuler, Aditya Bhaskara, Gang Fu, Vahab Mirrokni, Afshin Rostamizadeh, Morteza Zadimoghaddam.
  ICML 2016.
  

Theses

• Transport and Beyond: Efficient Optimization over Probability Distributions
  PhD Thesis, MIT, 2022. Advised by Pablo Parrilo.
  George M. Sprowls Award for Best MIT PhD Thesis in Artificial Intelligence & Decision Making

• Greed, hedging, and acceleration in convex optimization
  Master's Thesis, MIT, 2018. Advised by Pablo Parrilo.
  

• Minimax rates for online learning with limited decision changes (superseded by this paper in MOR/COLT)
  Undergrad thesis, Princeton CS department, 2016. Advised by Elad Hazan.
  

• Probabilistic linear Boolean classification
  Undergrad thesis, Princeton math department, 2016. Advised by Emmanuel Abbe.
  

Teaching

• STAT 9912: Acceleration and Hedging in Optimization -- Fall 2025 (New course, grad course)
• STAT 4300: Probability -- Spring 2025 (Undergraduate Teaching Excellence Award)
• STAT 9910: Stability in Optimization and Statistics -- Fall 2024 (New course, grad course)
• STAT 4300: Probability -- Spring 2024 (Undergraduate Teaching Excellence Award)

Disambiguation