Ilias Zadik, Assistant Professor of Statistics and Data Science

Ilias Zadik is an Assistant Professor of Statistics and Data Science at Yale University, His research mainly focuses on the mathematical theory of statistics and its many connections with other fields such as computer science, probability theory, and statistical physics. His primary area of interest is the study of “computational-statistical trade-offs”, where the goal is to understand whether computational bottlenecks are unavoidable in modern statistical models or a limitation of currently used techniques. Prior to Yale, he held postdoctoral positions at MIT and NYU. He received his PhD from MIT in 2019.

What do you do with data science?

My work studies the mathematics of data science. I aim to build algorithms with provable guarantees and theoretical tools that bring insights into the computational and statistical challenges of modern data science. Some of my work in the area includes a) the study of the computational complexity of accurate inference using large datasets (e.g, [1], [2], [3]) b) the study of differential privacy in the context of high dimensional estimation (e.g, [4], [5]), and c) the study of sharp phase transitions in high dimensional statistics (e.g., [6]) [1] Sparse high-dimensional linear regression. Estimating squared error and a phase transition, D. Gamarnik, I. Zadik, Annals of Statistics, 2022 [2] On the cryptographic hardness of learning single periodic neurons, J. Bruna, MJ Song, I. Zadik, NeurIPS 2021 [3] Free energy wells and overlap gap property in sparse PCA, GB Arous, A. Wein, I. Zadik, Communications on Pure and Applied Math, 2022 [4] Optimal private median estimation under minimal distributional assumptions, C Tzamos, EV Vlatakis-Gkaragkounis, I Zadik, NeurIPS, 2020 [5] Revealing network structure, confidentially: Improved rates for node-private graphon estimation, C Borgs, J Chayes, A Smith, I Zadik, FOCS, 2018 [6] The all-or-nothing phenomenon in sparse linear regression, G. Reeves, J. Xu, I. Zadik, Mathematical Statistics and Learning, 2021