Preprints

M. Celentano, W. S. DeWitt, S. Prillo, and Y. Song. Exact and efficient phylodynamic simulation from arbitrarily large populations, 2024+. arXiv

M. Celentano, L. Lin, Z. Fan, and S. Mei. Mean-field variational inference with the TAP free energy: Geometric and statistical properties in linear models. Preprint, 2023+. arXiv

M. Celentano, M. J. Wainwright. Challenges of the inconsistency regime: Novel debiasing methods for missing data models. Preprint, 2023+. arxiv github

S. Paik, M. Celentano, A. Green, R. Tibshirani. Maximum Mean Discrepancy Meets Neural Networks: The Radon-Kolmogorov-Smirnov Test. Preprint, 2023+. arxiv

M. Celentano, C. Cheng, A. Montanari. The high-dimensional asymptotics of first order methods with random data. Major revision at Annals of Applied Probability, 2021+. arxiv

M. Celentano, A. Montanari. CAD: Debiasing the Lasso with inaccurate covariate model. Major revision at Journal of Royal Statistical Society, Series B, 2021+. arxiv

M. Celentano, T. Misiakiewicz, A. Montanari. Minimum complexity interpolation in random features models. Preprint, 2021. arxiv

Publications

M. Celentano. Sudakov-Fernique post-AMP, and a new proof of the local convexity of the TAP free energy. Accepted at Annals of Probability, 2023. arxiv

M. Celentano, A. Montanari, Y. Wei. The Lasso with general Gaussian designs with applications to hypothesis testing. Annals of Statistics, 2023. journal arxiv talk

M. Celentano, Z. Fan, S. Mei. Local convexity of the TAP free energy and AMP convergence for Z2-synchronization. Annals of Statistics, 2023. journal arxiv

M. Celentano, A. Montanari. Fundamental barriers to high-dimensional regression with convex penalties. Annals of Statistics, 2021. journal arxiv

M. Celentano, A. Montanari, Y. Wu. The estimation error of general first order methods. COLT, 2020. conference arxiv

M. Celentano. Approximate separability of symmetrically penalized least squares in high dimensions: characterization and consequences. Information and Inference: A Journal of the IMA, 2020. journal arxiv