Embedded Files
I am spending the 2025-26 academic year as an associate research scientist (postdoc) at the Department of Electrical & Computer Engineering, Yale, where I am hosted by Boris Landa.
Before that, I was a postdoctoral researcher at the Department of Statistics, Stanford, where my stay was sponsored by David Donoho. Even before that, I was a PhD student at the School of Computer Science and Engineering, the Hebrew University of Jerusalem, where I was advised by Or Ordentlich and Matan Gavish. Much, much before that, dinosaurs roamed the earth.
Research interests: Information theory and signal processing, high-dimensional statistics, mathematics of data science.
Email: elad.romanov "at" gmail "dot" com
Preprints:
Preprints:
Michael J. Feldman, Theodor Misiakiewicz, and Elad Romanov, "Sparse PCA: Phase Transitions in the Critical Sparsity Regime", 2024
Publications:
Publications:
Alden Green and Elad Romanov*, "The High-Dimensional Asymptotics of Principal Component Regression", Annals of Statistics, 2025
Elad Romanov, Fangzhao Zhang, and Mert Pilanci, "Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing", ICLR, 2025
Elad Romanov, "On the Noise Sensitivity of the Randomized SVD", IEEE Transactions on Information Theory, 2024
Matan Gavish, William Leeb and Elad Romanov*, "Matrix Denoising with Partial Noise Statistics: Optimal Singular Value Shrinkage of Spiked F-Matrices", Information and Inference: A Journal of the IMA, 2022
David Donoho, Matan Gavish and Elad Romanov*, "ScreeNOT: Exact MSE-Optimal Singular Value Thresholding in Correlated Noise", Annals of Statistics, 2023
Elad Romanov, Gil Kur and Boaz Nadler, "Tyler's and Maronna's M-estimators: Non-Asymptotic Concentration Results", Journal of Multivariate Analysis, 2023
Elad Romanov, Tamir Bendory and Or Ordentlich, "On the Role of Channel Capacity in Learning Gaussian Mixture Models", COLT, 2022
Elad Romanov and Or Ordentlich, "Spiked Covariance Estimation from Modulo-Reduced Measurements", AISTATS, 2022
Elad Romanov, Tamir Bendory and Or Ordentlich, "Multi-Reference Alignment in High Dimensions: Sample Complexity and Phase Transition", SIAM Journal on Mathematics of Data Science, 2021
Elad Romanov and Or Ordentlich, "Blind Unwrapping of Modulo Reduced Gaussian Vectors: Recovering MSBs from LSBs", IEEE Transactions on Information Theory, 2021; [erratum]
William Leeb and Elad Romanov*, "Optimal Spectral Shrinkage and PCA With Heteroscedastic Noise", IEEE Transactions on Information Theory, 2021
Elad Romanov and Or Ordentlich, "On Compressed Sensing of Binary Signals for the Unsourced Random Access Channel", Entropy Special Issue on Information-Theoretic Aspects of Non-orthogonal and Massive Access for Future Wireless Networks, 2021
Elad Romanov and Matan Gavish, "The Noise-Sensitivity Phase Transition in Spectral Group Synchronization Over Compact Groups", Applied and Computational Harmonic Analysis, 2020
Elad Romanov and Or Ordentlich, "Above the Nyquist Rate, Modulo Folding Does Not Hurt", IEEE Signal Processing Letters, 2019
Elad Romanov and Matan Gavish, "Near-optimal matrix recovery from random linear measurements", Proceedings of the National Academy of Sciences, 2018
(* = Alphabetical ordering --- my preference nowadays.)
Google Sites
Report abuse