Patrik Róbert Gerber

I am an Applied Mathematics PhD student at MIT, supervised by Prof. Philippe Rigollet. Prior to MIT I obtained a Master’s in Mathematics and Statistics from the University of Oxford. My recent work has focused on the theory of likelihood-free inference.

Research

  1. Density estimation using the perceptron Patrik Róbert Gerber, Tianze Jiang, Yury Polyanskiy and Rui Sun arxiv:2312.17701 (2023) [abstract] [arXiv]
  2. Kernel-Based Tests for Likelihood-Free Hypothesis Testing Patrik Róbert Gerber, Tianze Jiang, Yury Polyanskiy and Rui Sun NeurIPS (2023) [abstract] [arXiv]
  3. Minimax optimal testing by classification Patrik Róbert Gerber, Yanjun Han and Yury Polyanskiy COLT (2023) [abstract] [arXiv]
  4. Likelihood-free hypothesis testing Patrik Róbert Gerber and Yury Polyanskiy arXiv:2211.01126 (2022) [abstract] [arXiv]
  5. Fisher information lower bounds for sampling Sinho Chewi, Patrik Róbert Gerber, Holden Lee and Chen Lu ALT (2022) [abstract] [arXiv]
  6. The query complexity of sampling from strongly log-concave distributions in one dimension Sinho Chewi, Patrik Róbert Gerber, Chen Lu, Thibaut Le Gouic and Philippe Rigollet COLT (2022) [abstract] [arXiv]
  7. Rejection sampling from shape-constrained distributions in sublinear time Sinho Chewi, Patrik Róbert Gerber, Chen Lu, Thibaut Le Gouic and Philippe Rigollet AISTATS (2022) [abstract] [arXiv]
  8. Gaussian discrepancy: a probabilistic relaxation of vector balancing Sinho Chewi, Patrik Róbert Gerber, Philippe Rigollet and Paxton Turner Discrete Applied Mathematics (2022) [abstract] [arXiv]
  9. Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent Jason M Altschuler, Sinho Chewi, Patrik Róbert Gerber and Austin J Stromme NeurIPS, Spotlight (2021) [abstract] [arXiv]

Teaching

Teaching Assistant

  • 6.3720/6.3722 — Introduction to Statistical Data Analysis (2024 Spring)
  • 18.821 — Mathematics Project Laboratory (2023 Fall)
  • 18.650 — Fundamentals of Statistics (2022 Fall, 2023 Spring)
  • 18.656/9.521/IDS.160 — Mathematical Statistics - A non-asymptotic approach (2022 Spring)
  • 15.070J/6.265J — Discrete Probability and Stochastic Processes (2021 Spring)
  • 18.675 — Theory of Probability (2020 Fall)

Academic mentor at √mathroots (2020, 2022)

√mathroots is a mathematical talent accelerator summer program for high-potential high school students from underrepresented backgrounds or underserved communities.