Bruno Loureiro

85 papers A* 17A 6B 1Journal 57Unranked 4

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models. CoRR Leonardo Defilippis, Florent Krzakala, Bruno Loureiro, Antoine Maillard
2026	J	`jnl`	A Random Matrix Theory of Masked Self-Supervised Regression. CoRR Arie Wortsman Zurich, Federica Gerace, Bruno Loureiro, Yue M. Lu
2026	J	`jnl`	Annealing in variational inference mitigates mode collapse: A theoretical study on Gaussian mixtures. CoRR Luigi Fogliani, Bruno Loureiro, Marylou Gabrié
2026	J	`jnl`	On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds. Trans. Mach. Learn. Res. Matteo Vilucchio, Nikolaos Tsilivis, Bruno Loureiro, Julia Kempe
2026	J	`jnl`	Optimal scaling laws in learning hierarchical multi-index models. CoRR Leonardo Defilippis, Florent Krzakala, Bruno Loureiro, Antoine Maillard
2026	J	`jnl`	The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling. CoRR Pierre-Alexandre Mattei, Bruno Loureiro
2026	J	`jnl`	When pre-training hurts LoRA fine-tuning: a dynamical analysis via single-index models. CoRR Gibbs Nwemadji, Bruno Loureiro, Jean Barbier
2025	A	`conf`	A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs. AISTATS Kasimir Tanner, Matteo Vilucchio, Bruno Loureiro, Florent Krzakala
2025	A	`conf`	A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities. AISTATS Yatin Dandi, Luca Pesce, Hugo Cui, Florent Krzakala, Yue M. Lu, Bruno Loureiro
2025	J	`jnl`	A theoretical perspective on mode collapse in variational inference. Mach. Learn. Sci. Technol. Roman Soletskyi, Marylou Gabrié, Bruno Loureiro
2025	J	`jnl`	Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks. CoRR Luca Arnaboldi, Bruno Loureiro, Ludovic Stephan, Florent Krzakala, Lenka Zdeborová
2025	J	`jnl`	Breaking the curse of dimensionality for linear rules: optimal predictors over the ellipsoid. CoRR Alexis Ayme, Bruno Loureiro
2025	J	`jnl`	Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data. CoRR Guillaume Braun, Bruno Loureiro, Ha Quang Minh, Masaaki Imaizumi
2025	A	`conf`	Fundamental computational limits of weak learnability in high-dimensional multi-index models. AISTATS Emanuele Troiani, Yatin Dandi, Leonardo Defilippis, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala
2025	J	`jnl`	Kernel ridge regression under power-law data: spectrum and generalization. CoRR Arie Wortsman, Bruno Loureiro
2025	J	`jnl`	On the existence of consistent adversarial attacks in high-dimensional linear classification. CoRR Matteo Vilucchio, Lenka Zdeborová, Bruno Loureiro
2025	J	`jnl`	Optimal Spectral Transitions in High-Dimensional Multi-Index Models. CoRR Leonardo Defilippis, Yatin Dandi, Pierre Mergny, Florent Krzakala, Bruno Loureiro
2025	J	`jnl`	Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime. CoRR Leonardo Defilippis, Yizhou Xu, Julius Girardin, Emanuele Troiani, Vittorio Erba, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala
2025	J	`jnl`	Statistical Advantage of Softmax Attention: Insights from Single-Location Regression. CoRR O. Duranthon, Pierre Marion, Claire Boyer, Bruno Loureiro, Lenka Zdeborová
2024	J	`jnl`	A High Dimensional Model for Adversarial Training: Geometry and Trade-Offs. CoRR Kasimir Tanner, Matteo Vilucchio, Bruno Loureiro, Florent Krzakala
2024	J	`jnl`	A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities. CoRR Yatin Dandi, Luca Pesce, Hugo Cui, Florent Krzakala, Yue M. Lu, Bruno Loureiro
2024	J	`jnl`	A theoretical perspective on mode collapse in variational inference. CoRR Roman Soletskyi, Marylou Gabrié, Bruno Loureiro
2024	A	`conf`	Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression. UAI Lucas Clarté, Adrien Vandenbroucque, Guillaume Dalle, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2024	J	`jnl`	Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression. CoRR Lucas Clarté, Adrien Vandenbroucque, Guillaume Dalle, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2024	A*	`conf`	Asymptotics of Learning with Deep Structured (Random) Features. ICML Dominik Schröder, Daniil Dmitriev, Hugo Cui, Bruno Loureiro
2024	J	`jnl`	Asymptotics of Learning with Deep Structured (Random) Features. CoRR Dominik Schröder, Daniil Dmitriev, Hugo Cui, Bruno Loureiro
2024	A*	`conf`	Asymptotics of feature learning in two-layer networks after one gradient-step. ICML Hugo Cui, Luca Pesce, Yatin Dandi, Florent Krzakala, Yue M. Lu, Lenka Zdeborová, Bruno Loureiro
2024	J	`jnl`	Asymptotics of feature learning in two-layer networks after one gradient-step. CoRR Hugo Cui, Luca Pesce, Yatin Dandi, Florent Krzakala, Yue M. Lu, Lenka Zdeborová, Bruno Loureiro
2024	A*	`conf`	Dimension-free deterministic equivalents and scaling laws for random feature regression. NeurIPS Leonardo Defilippis, Bruno Loureiro, Theodor Misiakiewicz
2024	J	`jnl`	Dimension-free deterministic equivalents for random feature regression. CoRR Leonardo Defilippis, Bruno Loureiro, Theodor Misiakiewicz
2024	J	`jnl`	Fundamental limits of weak learnability in high-dimensional multi-index models. CoRR Emanuele Troiani, Yatin Dandi, Leonardo Defilippis, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala
2024	J	`jnl`	How Two-Layer Neural Networks Learn, One (Giant) Step at a Time. J. Mach. Learn. Res. Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan
2024	J	`jnl`	On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds. CoRR Matteo Vilucchio, Nikolaos Tsilivis, Bruno Loureiro, Julia Kempe
2024	J	`jnl`	Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs. CoRR Luca Arnaboldi, Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan
2024	A*	`conf`	Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs. ICML Luca Arnaboldi, Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan
2023	A*	`conf`	Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation. ICML Luca Pesce, Florent Krzakala, Bruno Loureiro, Ludovic Stephan
2023	J	`jnl`	Are Gaussian data all you need? Extents and limits of universality in high-dimensional generalized linear estimation. CoRR Luca Pesce, Florent Krzakala, Bruno Loureiro, Ludovic Stephan
2023	J	`jnl`	Bayesian Inference With Nonlinear Generative Models: Comments on Secure Learning. IEEE Trans. Inf. Theory Ali Bereyhi, Bruno Loureiro, Florent Krzakala, Ralf R. Müller, Hermann Schulz-Baldes
2023	A*	`conf`	Deterministic equivalent and error universality of deep random features learning. ICML Dominik Schröder, Hugo Cui, Daniil Dmitriev, Bruno Loureiro
2023	J	`jnl`	Deterministic equivalent and error universality of deep random features learning. CoRR Dominik Schröder, Hugo Cui, Daniil Dmitriev, Bruno Loureiro
2023	J	`jnl`	Error scaling laws for kernel classification under source and capacity conditions. Mach. Learn. Sci. Technol. Hugo Cui, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2023	J	`jnl`	Escaping mediocrity: how two-layer networks learn hard single-index models with SGD. CoRR Luca Arnaboldi, Florent Krzakala, Bruno Loureiro, Ludovic Stephan
2023	A	`conf`	Expectation consistency for calibration of neural networks. UAI Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2023	J	`jnl`	Expectation consistency for calibration of neural networks. CoRR Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2023	A*	`conf`	From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks. COLT Luca Arnaboldi, Ludovic Stephan, Florent Krzakala, Bruno Loureiro
2023	J	`jnl`	From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks. CoRR Luca Arnaboldi, Ludovic Stephan, Florent Krzakala, Bruno Loureiro
2023	J	`jnl`	High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality. CoRR Urte Adomaityte, Leonardo Defilippis, Bruno Loureiro, Gabriele Sicuro
2023	J	`jnl`	Learning Two-Layer Neural Networks, One (Giant) Step at a Time. CoRR Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan
2023	J	`jnl`	Learning curves for the multi-class teacher-student perceptron. Mach. Learn. Sci. Technol. Elisabetta Cornacchia, Francesca Mignacco, Rodrigo Veiga, Cédric Gerbelot, Bruno Loureiro, Lenka Zdeborová
2023	A	`conf`	On double-descent in uncertainty quantification in overparametrized models. AISTATS Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2023	J	`jnl`	Theoretical characterization of uncertainty in high-dimensional linear classification. Mach. Learn. Sci. Technol. Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2023	A*	`conf`	Universality laws for Gaussian mixtures in generalized linear models. NeurIPS Yatin Dandi, Ludovic Stephan, Florent Krzakala, Bruno Loureiro, Lenka Zdeborová
2022	J	`jnl`	A study of uncertainty quantification in overparametrized high-dimensional models. CoRR Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2022	J	`jnl`	Bayesian Inference with Nonlinear Generative Models: Comments on Secure Learning. CoRR Ali Bereyhi, Bruno Loureiro, Florent Krzakala, Ralf R. Müller, Hermann Schulz-Baldes
2022	J	`jnl`	Coordinated Robotic Exploration of Dynamic Open Ocean Phenomena. Field Robotics José Pinto, Maria Costa, Renato Mendes, Keila Lima, Paulo Sousa Dias, João Pereira, Manuel A. Ribeiro, Renato Campos, Maria Paola Tomasino, Catarina Magalhães, Francisco López Castejón, Javier Gilabert, Adriana M. Santos-Ferreira, José C. B. da Silva, Paulo Relvas, Trent Lukaczyk, Kay Arne Skarpnes, Emlyn J. Davies, Alexander Chekalyuk, Bruno Loureiro, Ian G. Brosnan, Jing Li, João Borges de Sousa, Kanna Rajan
2022	J	`jnl`	Error Rates for Kernel Classification under Source and Capacity Conditions. CoRR Hugo Cui, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2022	A*	`conf`	Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension. ICML Bruno Loureiro, Cédric Gerbelot, Maria Refinetti, Gabriele Sicuro, Florent Krzakala
2022	J	`jnl`	Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension. CoRR Bruno Loureiro, Cédric Gerbelot, Maria Refinetti, Gabriele Sicuro, Florent Krzakala
2022	J	`jnl`	Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension. CoRR Federica Gerace, Florent Krzakala, Bruno Loureiro, Ludovic Stephan, Lenka Zdeborová
2022	J	`jnl`	Learning curves for the multi-class teacher-student perceptron. CoRR Elisabetta Cornacchia, Francesca Mignacco, Rodrigo Veiga, Cédric Gerbelot, Bruno Loureiro, Lenka Zdeborová
2022	A*	`conf`	Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks. NeurIPS Rodrigo Veiga, Ludovic Stephan, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2022	J	`jnl`	Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks. CoRR Rodrigo Veiga, Ludovic Stephan, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2022	B	`conf`	Secure Coding via Gaussian Random Fields. ISIT Ali Bereyhi, Bruno Loureiro, Florent Krzakala, Ralf R. Müller, Hermann Schulz-Baldes
2022	J	`jnl`	Secure Coding via Gaussian Random Fields. CoRR Ali Bereyhi, Bruno Loureiro, Florent Krzakala, Ralf R. Müller, Hermann Schulz-Baldes
2022	A*	`conf`	Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap. NeurIPS Luca Pesce, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2022	J	`jnl`	Subspace clustering in high-dimensions: Phase transitions \& Statistical-to-Computational gap. CoRR Luca Pesce, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2022	J	`jnl`	Theoretical characterization of uncertainty in high-dimensional linear classification. CoRR Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2021	J	`jnl`	Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model. CoRR Bruno Loureiro, Cédric Gerbelot, Hugo Cui, Sebastian Goldt, Florent Krzakala, Marc Mézard, Lenka Zdeborová
2021	A*	`conf`	Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime. NeurIPS Hugo Cui, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2021	J	`jnl`	Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime. CoRR Hugo Cui, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2021	J	`jnl`	Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions. CoRR Bruno Loureiro, Gabriele Sicuro, Cédric Gerbelot, Alessandro Pacco, Florent Krzakala, Lenka Zdeborová
2021	A*	`conf`	Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions. NeurIPS Bruno Loureiro, Gabriele Sicuro, Cédric Gerbelot, Alessandro Pacco, Florent Krzakala, Lenka Zdeborová
2021	A*	`conf`	Learning curves of generic features maps for realistic datasets with a teacher-student model. NeurIPS Bruno Loureiro, Cédric Gerbelot, Hugo Cui, Sebastian Goldt, Florent Krzakala, Marc Mézard, Lenka Zdeborová
2021	—	`conf`	The Gaussian equivalence of generative models for learning with shallow neural networks. MSML Sebastian Goldt, Bruno Loureiro, Galen Reeves, Florent Krzakala, Marc Mézard, Lenka Zdeborová
2021	J	`jnl`	The Spiked Matrix Model With Generative Priors. IEEE Trans. Inf. Theory Benjamin Aubin, Bruno Loureiro, Antoine Maillard, Florent Krzakala, Lenka Zdeborová
2020	—	`conf`	Exact asymptotics for phase retrieval and compressed sensing with random generative priors. MSML Benjamin Aubin, Bruno Loureiro, Antoine Baker, Florent Krzakala, Lenka Zdeborová
2020	A*	`conf`	Generalisation error in learning with random features and the hidden manifold model. ICML Federica Gerace, Bruno Loureiro, Florent Krzakala, Marc Mézard, Lenka Zdeborová
2020	J	`jnl`	Generalisation error in learning with random features and the hidden manifold model. CoRR Federica Gerace, Bruno Loureiro, Florent Krzakala, Marc Mézard, Lenka Zdeborová
2020	A*	`conf`	Phase retrieval in high dimensions: Statistical and computational phase transitions. NeurIPS Antoine Maillard, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2020	J	`jnl`	Phase retrieval in high dimensions: Statistical and computational phase transitions. CoRR Antoine Maillard, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová
2020	—	`conf`	To Boldly Dive Where No One Has Gone Before: Experiments in Coordinated Robotic Ocean Exploration. ISER José Pinto, Maria Costa, Keila Lima, Paulo Sousa Dias, João Pereira, Manuel A. Ribeiro, Renato Campos, Zara Mirmalek, Renato Mendes, Francisco López Castejón, Javier Gilabert, Maria Paola Tomasino, Catarina Magalhães, José C. B. da Silva, Paulo Relvas, Trent Lukaczyk, Kay Arne Skarpnes, Martin Ludvigsen, Alexander Chekalyuk, Bruno Loureiro, Ian G. Brosnan, Jing Li, Ami Hannon, João Borges de Sousa, Kanna Rajan
2019	J	`jnl`	Exact asymptotics for phase retrieval and compressed sensing with random generative priors. CoRR Benjamin Aubin, Bruno Loureiro, Antoine Baker, Florent Krzakala, Lenka Zdeborová
2019	A*	`conf`	The spiked matrix model with generative priors. NeurIPS Benjamin Aubin, Bruno Loureiro, Antoine Maillard, Florent Krzakala, Lenka Zdeborová
2019	J	`jnl`	The spiked matrix model with generative priors. CoRR Benjamin Aubin, Bruno Loureiro, Antoine Maillard, Florent Krzakala, Lenka Zdeborová
2017	—	`conf`	EVERUN: Enabling Power Consumption Monitoring in Underwater Networking Platforms. WiNTECH Giannis Kazdaridis, Stratos Keranidis, Polychronis Symeonidis, Paulo Sousa Dias, Pedro Gonçalves, Bruno Loureiro, Petrika Gjanci, Chiara Petrioli