Publications

Afonso S Bandeira, Antoine Maillard, Shahar Mendelson, Elliot Paquette (2023). Fitting an ellipsoid to a quadratic number of random points. arXiv preprint arXiv:2307.01181.

PDF Cite

Antoine Maillard, Afonso S Bandeira, David Belius, Ivan Dokmanić, Shuta Nakajima (2023). Injectivity of ReLU networks: perspectives from statistical physics. arXiv preprint arXiv:2302.14112.

PDF Cite

Jonathan Dong, Lorenzo Valzania, Antoine Maillard, Thanh-an Pham, Sylvain Gigan, Michael Unser (2023). Phase Retrieval: From Computational Imaging to Machine Learning: A tutorial. IEEE Signal Processing Magazine.

PDF Cite

Afonso S Bandeira, Antoine Maillard, Richard Nickl, Sven Wang (2023). On free energy barriers in Gaussian priors and failure of cold start MCMC for high-dimensional unimodal distributions. Philosophical Transactions of the Royal Society A.

PDF Cite

Emanuele Troiani, Vittorio Erba, Florent Krzakala, Antoine Maillard, Lenka Zdeborová (2022). Optimal denoising of rotationally invariant rectangular matrices. Mathematical and Scientific Machine Learning.

PDF Cite

Antoine Maillard, Florent Krzakala, Marc Mézard, Lenka Zdeborová (2022). Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising. Journal of Statistical Mechanics: Theory and Experiment.

PDF Cite

Afonso S Bandeira, Antoine Maillard, Nikita Zhivotovskiy (2022). A remark on Kashin’s discrepancy argument and partial coloring in the Komlós conjecture. Portugaliae Mathematica.

PDF Cite

Antoine Maillard, Florent Krzakala, Yue M Lu, Lenka Zdeborová (2022). Construction of optimal spectral methods in phase retrieval. Mathematical and Scientific Machine Learning.

PDF Cite

Antoine Maillard (2021). Fundamental limits of high-dimensional estimation. PhD Thesis.

PDF Cite

Antoine Maillard (2021). Large deviations of extreme eigenvalues of generalized sample covariance matrices. EPL (Europhysics Letters).

PDF Cite

Antoine Maillard, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová (2020). Phase retrieval in high dimensions: Statistical and computational phase transitions. NeurIPS 2020.

PDF Cite

Benjamin Aubin, Bruno Loureiro, Antoine Maillard, Florent Krzakala, Lenka Zdeborová (2020). The spiked matrix model with generative priors. IEEE Transactions on Information Theory.

PDF Cite

Antoine Maillard, Gérard Ben Arous, Giulio Biroli (2020). Landscape complexity for the empirical risk of generalized linear models. Mathematical and Scientific Machine Learning.

PDF Cite URL

Antoine Maillard, Laura Foini, Alejandro Lage Castellanos, Florent Krzakala, Marc Mézard, Lenka Zdeborová (2019). High-temperature expansions and message passing algorithms. Journal of Statistical Mechanics: Theory and Experiment.

PDF Cite

Corentin Bertrand, Olivier Parcollet, Antoine Maillard, Xavier Waintal (2019). Quantum Monte Carlo algorithm for out-of-equilibrium Green's functions at long times. Physical Review B.

PDF Cite

Benjamin Aubin, Antoine Maillard, Jean Barbier, Florent Krzakala, Nicolas Macris, Lenka Zdeborová (2019). The committee machine: computational to statistical gaps in learning a two-layers neural network. Journal of Statistical Mechanics: Theory and Experiment.

PDF Cite

M Schenk, X Buffat, K Li, A Maillard (2018). Vlasov description of the effects of nonlinear chromaticity on transverse coherent beam instabilities. Physical Review Accelerators and Beams.

PDF Cite

Jean Barbier, Nicolas Macris, Antoine Maillard, Florent Krzakala (2018). The mutual information in random linear estimation beyond iid matrices. 2018 IEEE International Symposium on Information Theory (ISIT).

PDF Cite

Michael Schenk, Xavier Buffat, Lee Carver, Kevin Li, Antoine Maillard, Elias Métral (2018). Experiments and Theory on Beam Stabilization with Second-Order Chromaticity. 61st ICFA ABDW on High-Intensity and High-Brightness Hadron Beams (HB'18), Daejeon, Korea, 17-22 June 2018.

PDF Cite

Stephen R Green, Antoine Maillard, Luis Lehner, Steven L Liebling (2015). Islands of stability and recurrence times in AdS. Physical Review D.

PDF Cite