Jason Altschuler

• Jason Altschuler and Sinho Chewi (2025), Shifted Composition I: Harnack and Reverse Transport Inequalities, IEEE Transactions on Information Theory , 71 (1), pp. 90-113.
• Jason Altschuler and Pablo Parrilo (2024), Acceleration by stepsize hedging: Silver Stepsize Schedule for smooth convex optimization, Mathematical Programming.
• Jason Altschuler and Pablo Parrilo (Forthcoming), Acceleration by Stepsize Hedging I: Multi-Step Descent and the Silver Stepsize Schedule.
• Jason Altschuler, Jinho Bok, Kunal Talwar (2024), On the privacy of Noisy Stochastic Gradient Descent for convex optimization, SIAM Journal on Computing , 53 (4), pp. 969-1001.
• Jinho Bok, Weijie Su, Jason Altschuler (Working), Shifted Interpolation for Differential Privacy.
• Jason Altschuler and Sinho Chewi (Working), Shifted Composition II: Shift Harnack Inequalities and Curvature Upper Bounds.
• Jason Altschuler and Kunal Talwar (Working), Resolving the mixing time of the Langevin Algorithm to its stationary distribution for log-concave sampling.
• Jason Altschuler and Pablo Parrilo (2023), Kernel approximation on algebraic varieties, SIAM Journal on Applied Algebra and Geometry , 7 (1), pp. 1-28.
• Jason Altschuler and Sinho Chewi (2023), Faster high-accuracy log-concave sampling via algorithmic warm starts, Journal of the ACM, 71 (3), pp. 1-55.
• Jason Altschuler and Enric Boix-Adsera (2023), Polynomial-time algorithms for Multimarginal Optimal Transport problems with structure, Mathematical Programming , 199 (p.p. 1107-1178).
• All Research from Jason Altschuler »

Current Courses

• STAT9912 - Sem In Adv Appl Of Stat: Acceleration And Hedging In Optimization

  This seminar will be taken by doctoral candidates after the completion of most of their coursework. Topics vary from year to year and are chosen from advance probability, statistical inference, robust methods, and decision theory with principal emphasis on applications.

  STAT9912301 ( Syllabus )

Past Courses

• AMCS5999 - Independent Study

  Independent Study allows students to pursue academic interests not available in regularly offered courses. Students must consult with their academic advisor to formulate a project directly related to the student�s research interests. All independent study courses are subject to the approval of the AMCS Graduate Group Chair.

• AMCS9999 - Ind Study & Research

  Study under the direction of a faculty member.

• STAT4300 - Probability

  Discrete and continuous sample spaces and probability; random variables, distributions, independence; expectation and generating functions; Markov chains and recurrence theory.

• STAT9910 - Sem in Adv Appl of Stat

  This seminar will be taken by doctoral candidates after the completion of most of their coursework. Topics vary from year to year and are chosen from advance probability, statistical inference, robust methods, and decision theory with principal emphasis on applications.

• STAT9912 - Sem in Adv Appl of Stat (OPT)

  This seminar will be taken by doctoral candidates after the completion of most of their coursework. Topics vary from year to year and are chosen from advance probability, statistical inference, robust methods, and decision theory with principal emphasis on applications.

• STAT9950 - Dissertation

  Dissertation

• Sloan Research Fellowship in Mathematics, 2025
• A.W. Tucker Finalist Prize, 2024
• George M. Sprowls Award for Best MIT PhD Thesis in Artificial Intelligence & Decision Making, 2023
• Two Sigma PhD Fellowship, 2020
• NSF Graduate Fellowship, 2016
• James Hayes-Edgar Palmer Prize in Engineering, Princeton University, 2016
• Accenture Prize in Computer Science, Princeton University, 2015

Knowledge @ Wharton

• Corporate Venturing Report, Knowledge @ Wharton - 08/05/2025
• In the Wake of Tariffs, Can Dynamic Pricing Work?, Knowledge @ Wharton - 08/05/2025
• The Rise of Crypto | Campbell Harvey and Neha Narula, Knowledge @ Wharton - 08/05/2025
• How Regulatory Enforcement and Transparency Could Bring Environmental Gains, Knowledge @ Wharton - 08/04/2025
• What I’ve Learned: Peter Cappelli, Knowledge @ Wharton - 08/04/2025
• Ferrero, Kellogg, and the Return of the Breakup-Merger Cycle, Knowledge @ Wharton - 08/01/2025
• How AI Is Reshaping Work and Higher Learning, Knowledge @ Wharton - 07/30/2025
• Inside Sprite, McDonald’s, and Dude Wipes: Branding That Sticks, Knowledge @ Wharton - 07/30/2025
• NFL Training Camps with Aaron Schatz, Chief Analytics Officer of FTN Fantasy, Knowledge @ Wharton - 07/30/2025
• Six Tactics to Get Better Results From AI, Knowledge @ Wharton - 07/29/2025