Roman Vershynin
Biography
Roman Vershynin, Ph.D., is Chancellor's Professor of Mathematics at the University of California, Irvine and Associate Director of the Center for Algorithms, Combinatorics and Optimization. His research focuses on high-dimensional probability and mathematical data science. Vershynin received his Ph.D. in Mathematics from the University of Missouri in 2000 under the supervision of Nigel Kalton. He held faculty positions at the University of California, Davis (2003-2008) and the University of Michigan (2008-2017) before joining UC Irvine in 2017.
Vershynin was selected to deliver an invited talk at the International Congress of Mathematicians in Hyderabad, India in 2010, and was elected to receive the IMS Medallion Award from the Institute of Mathematical Statistics in 2022. He received the Bessel Research Award from the Humboldt Research Foundation in 2013 and the PROSE Award in Mathematics from the Association of American Publishers in 2019 for his textbook "High-dimensional probability: An introduction with applications in data science." His work has been supported by multiple grants from the National Science Foundation, the U.S. Air Force, and the U.S. Army, as well as a Sloan Research Fellowship in 2005.
Vershynin has supervised seven Ph.D. students and mentored six postdoctoral fellows who have gone on to faculty positions at institutions including UCLA, Princeton University, UC Berkeley, UC Davis, and the University of British Columbia. He serves on the editorial boards of several journals including Bernoulli Journal, Annals of Applied Probability, and Annals of Statistics, and was a founding editor of Mathematical Statistics and Learning. Vershynin has organized numerous workshops and summer schools, including chairing the MSRI Introductory Workshop on phenomena in high dimensions in 2017.
Return to topEducation
- M.S. in Mathematics, Kharkiv National University, 1996
- Ph.D. in Mathematics, University of Missouri, 2000
Distinctions
- Invited talk at the International Congress of Mathematicians, Hyderabad, India, 2010
- IMS Medallion Award, Institute of Mathematical Statistics, 2022
- PROSE Award in Mathematics, Association of American Publishers, 2019
- Bessel Research Award, Humboldt Research Foundation, 2013
- Sloan Research Fellowship, Alfred P. Sloan Foundation, 2005
- Young Author Best Paper Award, IEEE J. Signal Processing, 2012
- Distinguished Mid-Career Faculty Award for Research, UCI, 2020
Areas of Expertise
- High-Dimensional Probability
- Random Matrix Theory
- Compressed Sensing Algorithms
- Covariance Matrix Estimation
- Differentially Private Synthetic Data
- Neural Network Capacity
- Community Detection Networks
Recent Publications
- Smirnov G., Vershynin R., “Thinning to Improve Two-Sample Discrepancy” (opens in new tab), Random Structures and Algorithms, vol. 68, 2026.
- Abdalla P., Vershynin R., “On the Dimension-Free Concentration of Simple Tensors via Matrix Deviation” (opens in new tab), Journal of Theoretical Probability, vol. 39, 2026.
- Ferber A., Han J., Mao D., Vershynin R., “Hamiltonicity of sparse pseudorandom graphs” (opens in new tab), Combinatorics Probability and Computing, vol. 34, pp. 596-620, 2025.
- He Y., Strohmer T., Vershynin R., Zhu Y., “Differentially private low-dimensional synthetic data from high-dimensional datasets” (opens in new tab), Information and Inference, vol. 14, 2025.
- Boedihardjo M., Strohmer T., Vershynin R., “COVARIANCE LOSS, SZEMEREDI REGULARITY, AND DIFFERENTIAL PRIVACY” (opens in new tab), Proceedings of the American Mathematical Society, vol. 153, pp. 773-782, 2025.
- Plan Y., Vershynin R., “Random matrices acting on sets: Independent columns” (opens in new tab), Electronic Journal of Probability, vol. 30, 2025.
- Ivanisvili P., Klein O., Vershynin R., “Covering the Hypercube, the Uncertainty Principle, and an Interpolation Formula” (opens in new tab), Electronic Journal of Combinatorics, vol. 32, 2025.
- Boedihardjo M., Strohmer T., Vershynin R., “Private measures, random walks, and synthetic data” (opens in new tab), Probability Theory and Related Fields, vol. 189, pp. 569-611, 2024.
- Boedihardjo M., Strohmer T., Vershynin R., “Covariance’s Loss is Privacy’s Gain: Computationally Efficient, Private and Accurate Synthetic Data” (opens in new tab), Foundations of Computational Mathematics, vol. 24, pp. 179-226, 2024.
- Baldi P., Vershynin R., “The quarks of attention: Structure and capacity of neural attention building blocks” (opens in new tab), Artificial Intelligence, vol. 319, 2023.
- Dover K., Cang Z., Ma A., Nie Q., Vershynin R., “AVIDA: An alternating method for visualizing and integrating data” (opens in new tab), Journal of Computational Science, vol. 68, 2023.
- Tan Y.S., Vershynin R., “Online Stochastic Gradient Descent with Arbitrary Initialization Solves Non-smooth, Non-convex Phase Retrieval”, Journal of Machine Learning Research, vol. 24, 2023.
- Boedihardjo M., Strohmer T., Vershynin R., “Privacy of Synthetic Data: A Statistical Framework” (opens in new tab), IEEE Transactions on Information Theory, vol. 69, pp. 520-527, 2023.
- Boedihardjo M., Strohmer T., Vershynin R., “Private Sampling: A Noiseless Approach for Generating Differentially Private Synthetic Data” (opens in new tab), SIAM Journal on Mathematics of Data Science, vol. 4, pp. 1082-1115, 2022.
- Baldi P., Vershynin R., “A theory of capacity and sparse neural encoding” (opens in new tab), Neural Networks, vol. 143, pp. 12-27, 2021.
- Bryson J., Vershynin R., Zhao H., “Marchenko-Pastur law with relaxed independence conditions” (opens in new tab), Random Matrices Theory and Application, vol. 10, 2021.
- Livshyts G.V., Tikhomirov K., Vershynin R., “THE SMALLEST SINGULAR VALUE OF INHOMOGENEOUS SQUARE RANDOM MATRICES” (opens in new tab), Annals of Probability, vol. 49, pp. 1286-1309, 2021.
Most Cited Publications
- Roman Vershynin, “High-dimensional probability. An introduction with applications in data science” (opens in new tab), High Dimensional Probability an Introduction with Applications in Data Science, Cambridge University Press, pp. 1-284, 2018.
- Needell D., Vershynin R., “Uniform uncertainty principle and signal recovery via regularized orthogonal matching pursuit” (opens in new tab), Foundations of Computational Mathematics, vol. 9, pp. 317-334, 2009.
- Needell D., Vershynin R., “Signal recovery from incomplete and inaccurate measurements via regularized orthogonal matching pursuit” (opens in new tab), IEEE Journal on Selected Topics in Signal Processing, vol. 4, pp. 310-316, 2010.
- Strohmer T., Vershynin R., “A randomized kaczmarz algorithm with exponential convergence” (opens in new tab), Journal of Fourier Analysis and Applications, vol. 15, pp. 262-278, 2009.
- Vershynin R., “Introduction to the non-asymptotic analysis of random matrices” (opens in new tab), Compressed Sensing Theory and Applications, pp. 210-268, 2009.
- Rudelson M., Vershynin R., “On sparse reconstruction from Fourier and Gaussian measurements” (opens in new tab), Communications on Pure and Applied Mathematics, vol. 61, pp. 1025-1045, 2008.
- Rudelson M., Vershynin R., “Hanson-Wright inequality and sub-gaussian concentration” (opens in new tab), Electronic Communications in Probability, vol. 18, 2013.
- Plan Y., Vershynin R., “Robust 1-bit compressed sensing and sparse logistic regression: A convex programming approach” (opens in new tab), IEEE Transactions on Information Theory, vol. 59, pp. 482-494, 2013.
- Plan Y., Vershynin R., “One-bit compressed sensing by linear programming” (opens in new tab), Communications on Pure and Applied Mathematics, vol. 66, pp. 1275-1297, 2013.
- Rudelson M., Vershynin R., “The Littlewood-Offord problem and invertibility of random matrices” (opens in new tab), Advances in Mathematics, vol. 218, pp. 600-633, 2008.
Contact Information
Website: https://www.math.uci.edu/~rvershyn
Email: rvershyn@uci.edu
Address: 540D Rowland Hall
Return to topThis profile was created with the help of AI.
Last updated on 5/26/2026.