Florent Krzakala

Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining COLT 2026 A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs AISTATS 2025 A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities AISTATS 2025 Fundamental computational limits of weak learnability in high-dimensional multi-index models AISTATS 2025 Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds ICML 2025 Fundamental Limits of Matrix Sensing: Exact Asymptotics, Universality, and Applications COLT 2025 Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression UAI 2024 Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity ICLR 2024 A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention NeurIPS 2024 Asymptotic Characterisation of the Performance of Robust Linear Regression in the Presence of Outliers AISTATS 2024 Asymptotics of feature learning in two-layer networks after one gradient-step ICML 2024 Bayes-optimal learning of an extensive-width neural network from quadratically many samples NeurIPS 2024 Fundamental Limits of Non-Linear Low-Rank Matrix Estimation COLT 2024 How Two-Layer Neural Networks Learn, One (Giant) Step at a Time JMLR 2024 Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs ICML 2024 Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models ICML 2024 The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents ICML 2024 Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation ICML 2023 Bayes-optimal Learning of Deep Random Networks of Extensive-width ICML 2023 Expectation consistency for calibration of neural networks UAI 2023 From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks COLT 2023 On double-descent in uncertainty quantification in overparametrized models AISTATS 2023 Optimal Algorithms for the Inhomogeneous Spiked Wigner Model NeurIPS 2023 Tree-AMP: Compositional Inference with Tree Approximate Message Passing JMLR 2023 Universality laws for Gaussian mixtures in generalized linear models NeurIPS 2023 Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension ICML 2022 Multi-layer State Evolution Under Random Convolutional Design NeurIPS 2022 Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks NeurIPS 2022 Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap NeurIPS 2022 Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed ICML 2021 Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime NeurIPS 2021 Learning curves of generic features maps for realistic datasets with a teacher-student model NeurIPS 2021 Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions NeurIPS 2021 Asymptotic Errors for High-Dimensional Convex Penalized Linear Regression beyond Gaussian Matrices COLT 2020 Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval NeurIPS 2020 Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures NeurIPS 2020 Double Trouble in Double Descent: Bias and Variance(s) in the Lazy Regime ICML 2020 Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification NeurIPS 2020 Generalisation error in learning with random features and the hidden manifold model ICML 2020 Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization NeurIPS 2020 Phase retrieval in high dimensions: Statistical and computational phase transitions NeurIPS 2020 Reservoir Computing meets Recurrent Kernels and Structured Transforms NeurIPS 2020 The Role of Regularization in Classification of High-dimensional Noisy Gaussian Mixture ICML 2020 Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup NeurIPS 2019 Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models ICML 2019 The spiked matrix model with generative priors NeurIPS 2019 Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models NeurIPS 2019 Entropy and mutual information in models of deep neural networks NeurIPS 2018 Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models COLT 2018 The committee machine: Computational to statistical gaps in learning a two-layers neural network NeurIPS 2018 Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula NeurIPS 2016 Matrix Completion from Fewer Entries: Spectral Detectability and Rank Estimation NeurIPS 2015 Swept Approximate Message Passing for Sparse Estimation ICML 2015 Training Restricted Boltzmann Machine via the Thouless-Anderson-Palmer free energy NeurIPS 2015 Spectral Clustering of graphs with the Bethe Hessian NeurIPS 2014 Blind Calibration in Compressed Sensing using Message Passing Algorithms NeurIPS 2013