Publications

Up-to-date full list of publications of L. Zdeborová is available on Google Scholar.

2023

Multi-layer state evolution under random convolutional design

M. Daniels; C. Gerbelot; F. Krzakala; L. Zdeborova 

Journal Of Statistical Mechanics-Theory And Experiment. 2023-11-01. Vol. 2023, num. 11, p. 114002. DOI : 10.1088/1742-5468/ad0220.

Backtracking Dynamical Cavity Method

F. Behrens; B. Hudcová; L. Zdeborová 

Physical Review X. 2023-08-21. Vol. 13, num. 3. DOI : 10.1103/PhysRevX.13.031021.

Error scaling laws for kernel classification under source and capacity conditions

H. C. Cui; B. Loureiro; F. Krzakala; L. Zdeborová 

IOPscience. 2023. num. Mach. Learn.: Sci. Technol. 4 035033. DOI : 10.1088/2632-2153/acf041.

Bayes-optimal Learning of Deep Random Networks of Extensive-width

H. C. Cui; F. Krzakala; L. Zdeborová 

2023. International Conference on Machine Learning, Honolulu, Hawaii, USA, July 23-29, 2023.

Expectation consistency for calibration of neural networks

L. A. Clarte; B. Loureiro; F. Krzakala; L. Zdeborová 

2023. Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023), PMLR 216:443–453., Pittsburgh, PA, USA, August 31-4, 2023.

Neural-prior stochastic block model

O. Duranthon; L. Zdeborová 

Machine Learning-Science And Technology. 2023-09-01. Vol. 4, num. 3, p. 035017. DOI : 10.1088/2632-2153/ace60f.

Theoretical characterization of uncertainty in high-dimensional linear classification

L. Clarte; B. Loureiro; F. Krzakala; L. Zdeborova 

Machine Learning-Science And Technology. 2023-06-01. Vol. 4, num. 2, p. 025029. DOI : 10.1088/2632-2153/acd749.

On double-descent in uncertainty quantification in overparametrized models

L. A. Clarte; B. Loureiro; F. Krzakala; L. Zdeborová 

2023. 26th International Conference on Artificial Intelligence and Statistics (AISTATS) , Palau de Congressos, Valencia, Spain, April 25-27, 2023. p. 7089-7125.

Tree-AMP: Compositional Inference with Tree Approximate Message Passing

A. Baker; B. Aubin; F. Krzakala; L. Zdeborová 

Journal of Machine Learning Research. 2023. Vol. 24, num. 57, p. 1–89.

Learning curves for the multi-class teacher-student perceptron

E. Cornacchia; F. Mignacco; R. Veiga; C. Gerbelot; B. Loureiro et al. 

Machine Learning-Science And Technology. 2023-03-01. Vol. 4, num. 1, p. 015019. DOI : 10.1088/2632-2153/acb428.

Bayesian reconstruction of memories stored in neural networks from their connectivity

S. Goldt; F. Krzakala; L. Zdeborová; N. Brunel 

PLoS Comput Biol. 2023-01-30. Vol. 19, p. e1010813. DOI : 10.1371/journal.pcbi.1010813.

2022

Multi-layer State Evolution Under Random Convolutional Design

M. Daniels; C. Gerbelot; F. Krzakala; L. Zdeborová 

NeurIPS Proceedings. 2022. 

Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap

L. Pesce; B. Loureiro; F. Krzakala; L. Zdeborová 

2022. 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans , November 28-December 9, 2022.

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

R. Veiga; L. Stephan; B. Loureiro; F. Krzakala; L. Zdeborová 

2022. 36th Conference on Neural Information Processing Systems (NeurIPS 2022), New Orleans, November 28-December 9, 2022.

Optimal denoising of rotationally invariant rectangular matrices

E. Troiani; V. Erba; F. Krzakala; A. Maillard; L. Zdeborová 

Proceedings of Mathematical and Scientific Machine Learning. 2022. Vol. 190, p. 97-112.

Planted XY model: Thermodynamics and inference

S. Chen; G. Huang; G. Piccioli; L. Zdeborová 

Physical Review E. 2022-11-07. Vol. 106, num. 5, p. 054115. DOI : 10.1103/PhysRevE.106.054115.

Planted matching problems on random hypergraphs

U. Adomaityte; A. Toshniwal; G. Sicuro; L. Zdeborová 

Physical Review E. 2022-11-07. Vol. 106, num. 5, p. 054302. DOI : 10.1103/PhysRevE.106.054302.

Disordered systems insights on computational hardness

D. Gamarnik; C. Moore; L. Zdeborova 

Journal Of Statistical Mechanics-Theory And Experiment. 2022-11-24. Vol. 2022, num. 11, p. 114015. DOI : 10.1088/1742-5468/ac9cc8.

Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*

H. Cui; B. Loureiro; F. Krzakala; L. Zdeborova 

Journal Of Statistical Mechanics-Theory And Experiment. 2022-11-01. Vol. 2022, num. 11, p. 114004. DOI : 10.1088/1742-5468/ac9829.

(Dis)assortative partitions on random regular graphs

F. Behrens; G. Arpino; Y. Kivva; L. Zdeborova 

Journal Of Physics A-Mathematical And Theoretical. 2022-09-30. Vol. 55, num. 39, p. 395004. DOI : 10.1088/1751-8121/ac8b46.

Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising

A. Maillard; F. Krzakala; M. Mézard; L. Zdeborová 

Journal of Statistical Mechanics: Theory and Experiment. 2022-08-10. Vol. 2022, num. 8, p. 083301. DOI : 10.1088/1742-5468/ac7e4c.

Aligning random graphs with a sub-tree similarity message-passing algorithm

G. Piccioli; G. Semerjian; G. Sicuro; L. Zdeborova 

Journal Of Statistical Mechanics-Theory And Experiment. 2022-06-01. Vol. 2022, num. 6, p. 063401. DOI : 10.1088/1742-5468/ac70d2.

Large deviations of semisupervised learning in the stochastic block model

H. Cui; L. Saglietti; L. Zdeborova 

Physical Review E. 2022-03-04. Vol. 105, num. 3, p. 034108. DOI : 10.1103/PhysRevE.105.034108.

Probing transfer learning with a model of synthetic correlated datasets

F. Gerace; L. Saglietti; S. Sarao Mannelli; A. Saxe; L. Zdeborová 

Machine Learning: Science and Technology. 2022-01-26. DOI : 10.1088/2632-2153/ac4f3f.

2021

Solvable Model for Inheriting the Regularization through Knowledge Distillation

L. Saglietti; L. Zdeborová 

2021-12-16. 2nd Mathematical and Scientific Machine Learning Conference, Online, August 16-19, 2021. p. 809-846.

The Gaussian equivalence of generative models for learning with shallow neural networks

S. Goldt; B. Loureiro; G. Reeves; F. Krzakala; M. Mezard et al. 

2021-12-16. 2nd Mathematical and Scientific Machine Learning Conference, Online, August 16-19, 2021.

Construction of optimal spectral methods in phase retrieval

A. Maillard; F. Krzakala; l. Yue; L. Zdeborová 

2021-08-16. 2nd Conference on Mathematical and Scientific Machine Learning (MSML 2021), Lausanne, Suisse, August 16-19, 2021. p. 693-720.

Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions

B. Loureiro; G. Sicuro; C. Gerbelot; A. Pacco; F. Krzakala et al. 

2021. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Online, December 7-10, 2021.

Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime

H. C. Cui; B. Loureiro; F. Krzakala; L. Zdeborová 

2021. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Online, December 7-10, 2021.

Large deviations in the perceptron model and consequences for active learning

H. Cui; L. Saglietti; L. Zdeborová 

Machine Learning: Science and Technology. 2021. Vol. 2, num. 4, p. 045001. DOI : 10.1088/2632-2153/abfbbb.

Learning curves of generic features maps for realistic datasets with a teacher-student model

B. Loureiro; C. Gerbelot; H. C. Cui; S. Goldt; F. Krzakala et al. 

2021. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Online, December 7-10, 2021. p. 16-58.

Generalisation error in learning with random features and the hidden manifold model*

F. Gerace; B. Loureiro; F. Krzakala; M. Mezard; L. Zdeborova 

Journal Of Statistical Mechanics-Theory And Experiment. 2021-12-01. Vol. 2021, num. 12, p. 124013. DOI : 10.1088/1742-5468/ac3ae6.

Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed

M. Refinetti; S. Goldt; F. Krzakala; L. Zdeborová 

2021-07-21. 38th International Conference on Machine Learning (ICML), Virtual, July 18-24, 2021. p. 8936-8947.

Epidemic mitigation by statistical inference from contact tracing data

A. Baker; I. Biazzo; A. Braunstein; G. Catania; L. Dall’Asta et al. 

Proceedings Of The National Academy Of Sciences Of The United States Of America. 2021-08-10. Vol. 118, num. 32, p. e2106548118. DOI : 10.1073/pnas.2106548118.

Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem

F. Mignacco; P. Urbani; L. Zdeborova 

Machine Learning-Science And Technology. 2021-09-01. Vol. 2, num. 3, p. 035029. DOI : 10.1088/2632-2153/ac0615.

The planted k-factor problem

G. Sicuro; L. Zdeborova 

Journal Of Physics A-Mathematical And Theoretical. 2021-04-30. Vol. 54, num. 17, p. 175002. DOI : 10.1088/1751-8121/abee9d.

2020

Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions

S. Sarao Manelli; E. Vanden-Eijnden; L. Zdeborová 

2020. Advances in Neural Information Processing Systems, Dec 6, 2020 – Dec 12, 2020. p. 13445–13455.

Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization

B. Aubin; F. Krzakala; L. Yue; L. Zdeborová 

2020. Advances in Neural Information Processing Systems, Dec 6, 2020 – Dec 12, 2020. p. 12199–12210.

Phase retrieval in high dimensions: Statistical and computational phase transitions

A. Maillard; B. Loureiro; F. Krzakala; L. Zdeborová 

2020. Advances in Neural Information Processing Systems, Dec 6, 2020 – Dec 12, 2020. p. 11071–11082.

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification

F. Mignacco; F. Krzakala; P. Urbani; L. Zdeborová 

2020. Advances in Neural Information Processing Systems, Dec 6, 2020 – Dec 12, 2020. p. 9540–955.

Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval

S. Sarao Mannelli; G. Biroli; C. Cammarota; F. Krzakala; P. Urbani et al. 

2020. Advances in Neural Information Processing Systems, Dec 6, 2020 – Dec 12, 2020. p. 3265–3274.

The Spiked Matrix Model With Generative Priors

B. Aubin; B. Loureiro; A. Maillard; F. Krzakala; L. Zdeborova 

IEEE Transactions on Information Theory. 2020-10-27. Vol. 67, num. 2, p. 1156-1181. DOI : 10.1109/TIT.2020.3033985.

Generalized approximate survey propagation for high-dimensional estimation

L. Saglietti; Y. M. Lu; C. Lucibello 

Journal Of Statistical Mechanics-Theory And Experiment. 2020-12-01. Vol. 2020, num. 12, p. 124003. DOI : 10.1088/1742-5468/abc62c.

Machine learning and statistical physics: preface

E. Agliari; A. Barra; P. Sollich; L. Zdeborova 

Journal Of Physics A-Mathematical And Theoretical. 2020-11-18. Vol. 53, num. 50, p. 500401. DOI : 10.1088/1751-8121/abca75.