Florent Krzakala

Orcid: 0000-0003-2313-2578

According to our database1, Florent Krzakala authored at least 179 papers between 2004 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Rigorous Dynamical Mean-Field Theory for Stochastic Gradient Descent Methods.
SIAM J. Math. Data Sci., 2024

A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities.
CoRR, 2024

Optical training of large-scale Transformers and deep neural networks with direct feedback alignment.
CoRR, 2024

The phase diagram of compressed sensing with ℓ<sub>0</sub>-norm regularization.
CoRR, 2024

Bayes-optimal learning of an extensive-width neural network from quadratically many samples.
CoRR, 2024

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs.
CoRR, 2024

Fundamental limits of weak learnability in high-dimensional multi-index models.
CoRR, 2024

Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions.
CoRR, 2024

Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression.
CoRR, 2024

A High Dimensional Model for Adversarial Training: Geometry and Trade-Offs.
CoRR, 2024

A phase transition between positional and semantic learning in a solvable model of dot-product attention.
CoRR, 2024

Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Asymptotics of feature learning in two-layer networks after one gradient-step.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Fundamental Limits of Non-Linear Low-Rank Matrix Estimation.
Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

Asymptotic Characterisation of the Performance of Robust Linear Regression in the Presence of Outliers.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023
Bayesian Inference With Nonlinear Generative Models: Comments on Secure Learning.
IEEE Trans. Inf. Theory, December, 2023

Error scaling laws for kernel classification under source and capacity conditions.
Mach. Learn. Sci. Technol., September, 2023

Asymptotic Errors for Teacher-Student Convex Generalized Linear Models (Or: How to Prove Kabashima's Replica Formula).
IEEE Trans. Inf. Theory, March, 2023

Bayesian reconstruction of memories stored in neural networks from their connectivity.
PLoS Comput. Biol., January, 2023

Tree-AMP: Compositional Inference with Tree Approximate Message Passing.
J. Mach. Learn. Res., 2023

Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective.
CoRR, 2023

Asymptotic Characterisation of Robust Empirical Risk Minimisation Performance in the Presence of Outliers.
CoRR, 2023

Escaping mediocrity: how two-layer networks learn hard single-index models with SGD.
CoRR, 2023

Learning Two-Layer Neural Networks, One (Giant) Step at a Time.
CoRR, 2023

Compressed sensing with l0-norm: statistical physics analysis and algorithms for signal recovery.
CoRR, 2023

Statistical mechanics of the maximum-average submatrix problem.
CoRR, 2023

Optimal Learning of Deep Random Networks of Extensive-width.
CoRR, 2023

Expectation consistency for calibration of neural networks.
Proceedings of the Uncertainty in Artificial Intelligence, 2023

Optimal Algorithms for the Inhomogeneous Spiked Wigner Model.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Universality laws for Gaussian mixtures in generalized linear models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Compressed sensing with ℓ0-norm: statistical physics analysis & algorithms for signal recovery.
Proceedings of the IEEE Information Theory Workshop, 2023

Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation.
Proceedings of the International Conference on Machine Learning, 2023

Bayes-optimal Learning of Deep Random Networks of Extensive-width.
Proceedings of the International Conference on Machine Learning, 2023

From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks.
Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

On double-descent in uncertainty quantification in overparametrized models.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022
A study of uncertainty quantification in overparametrized high-dimensional models.
CoRR, 2022

Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension.
CoRR, 2022

Theoretical characterization of uncertainty in high-dimensional linear classification.
CoRR, 2022

Error Rates for Kernel Classification under Source and Capacity Conditions.
CoRR, 2022

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Multi-layer State Evolution Under Random Convolutional Design.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Optimal denoising of rotationally invariant rectangular matrices.
Proceedings of the Mathematical and Scientific Machine Learning, 2022

Secure Coding via Gaussian Random Fields.
Proceedings of the IEEE International Symposium on Information Theory, 2022

Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension.
Proceedings of the International Conference on Machine Learning, 2022

Adversarial Robustness by Design Through Analog Computing And Synthetic Gradients.
Proceedings of the IEEE International Conference on Acoustics, 2022

2021
The Spiked Matrix Model With Generative Priors.
IEEE Trans. Inf. Theory, 2021

Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising.
CoRR, 2021

Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions.
CoRR, 2021

Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model.
CoRR, 2021

Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Learning curves of generic features maps for realistic datasets with a teacher-student model.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Construction of optimal spectral methods in phase retrieval.
Proceedings of the Mathematical and Scientific Machine Learning, 2021

The Gaussian equivalence of generative models for learning with shallow neural networks.
Proceedings of the Mathematical and Scientific Machine Learning, 2021

Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed.
Proceedings of the 38th International Conference on Machine Learning, 2021

LightOn Optical Processing Unit : Scaling-up AI and HPC with a Non von Neumann co-processor.
Proceedings of the IEEE Hot Chips 33 Symposium, 2021

2020
Mutual Information and Optimality of Approximate Message-Passing in Random Linear Estimation.
IEEE Trans. Inf. Theory, 2020

Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment.
CoRR, 2020

Epidemic mitigation by statistical inference from contact tracing data.
CoRR, 2020

The Gaussian equivalence of generative models for learning with two-layer neural networks.
CoRR, 2020

Light-in-the-loop: using a photonics co-processor for scalable training of neural networks.
CoRR, 2020

TRAMP: Compositional Inference with TRee Approximate Message Passing.
CoRR, 2020

The role of regularization in classification of high-dimensional noisy Gaussian mixture.
CoRR, 2020

Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction.
CoRR, 2020

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Phase retrieval in high dimensions: Statistical and computational phase transitions.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Reservoir Computing meets Recurrent Kernels and Structured Transforms.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Exact asymptotics for phase retrieval and compressed sensing with random generative priors.
Proceedings of Mathematical and Scientific Machine Learning, 2020

Rademacher complexity and spin glasses: A link between the replica and statistical theories of learning.
Proceedings of Mathematical and Scientific Machine Learning, 2020

Double Trouble in Double Descent: Bias and Variance(s) in the Lazy Regime.
Proceedings of the 37th International Conference on Machine Learning, 2020

The Role of Regularization in Classification of High-dimensional Noisy Gaussian Mixture.
Proceedings of the 37th International Conference on Machine Learning, 2020

Generalisation error in learning with random features and the hidden manifold model.
Proceedings of the 37th International Conference on Machine Learning, 2020

Kernel Computations from Large-Scale Random Features Obtained by Optical Processing Units.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Asymptotic Errors for High-Dimensional Convex Penalized Linear Regression beyond Gaussian Matrices.
Proceedings of the Conference on Learning Theory, 2020

2019
Decoding From Pooled Data: Phase Transitions of Message Passing.
IEEE Trans. Inf. Theory, 2019

Decoding from Pooled Data: Sharp Information-Theoretic Bounds.
SIAM J. Math. Data Sci., 2019

Blind calibration for compressed sensing: State evolution and an online algorithm.
CoRR, 2019

Modelling the influence of data structure on learning in neural networks.
CoRR, 2019

Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model.
CoRR, 2019

Optical Reservoir Computing using multiple light scattering for chaotic systems prediction.
CoRR, 2019

High-temperature Expansions and Message Passing Algorithms.
CoRR, 2019

On the Universality of Noiseless Linear Estimation with Respect to the Measurement Matrix.
CoRR, 2019

Principled Training of Neural Networks with Direct Feedback Alignment.
CoRR, 2019

Passed & Spurious: analysing descent algorithms and local minima in spiked matrix-tensor model.
CoRR, 2019

Generalisation dynamics of online learning in over-parameterised neural networks.
CoRR, 2019

Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models.
Proceedings of the 36th International Conference on Machine Learning, 2019

Spectral Method for Multiplexed Phase Retrieval and Application in Optical Imaging in Complex Media.
Proceedings of the IEEE International Conference on Acoustics, 2019

Blind Calibration for Sparse Regression: A State Evolution Analysis.
Proceedings of the 8th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, 2019

2018
Marvels and Pitfalls of the Langevin Algorithm in Noisy High-dimensional Inference.
CoRR, 2018

Rank-one matrix estimation: analysis of algorithmic and information theoretic limits by the spatial coupling method.
CoRR, 2018

Approximate message-passing for convex optimization with non-separable penalties.
CoRR, 2018

Approximate Survey Propagation for Statistical Inference.
CoRR, 2018

Scaling Up Echo-State Networks With Multiple Light Scattering.
Proceedings of the 2018 IEEE Statistical Signal Processing Workshop, 2018

Entropy and mutual information in models of deep neural networks.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

The committee machine: Computational to statistical gaps in learning a two-layers neural network.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

The Mutual Information in Random Linear Estimation Beyond i.i.d. Matrices.
Proceedings of the 2018 IEEE International Symposium on Information Theory, 2018

Estimation in the Spiked Wigner Model: A Short Proof of the Replica Formula.
Proceedings of the 2018 IEEE International Symposium on Information Theory, 2018

Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models.
Proceedings of the Conference On Learning Theory, 2018

2017
Performance Limits for Noisy Multimeasurement Vector Problems.
IEEE Trans. Signal Process., 2017

Approximate Message-Passing Decoder and Capacity Achieving Sparse Superposition Codes.
IEEE Trans. Inf. Theory, 2017

Robust Phase Retrieval with the Swept Approximate Message Passing (prSAMP) Algorithm.
Image Process. Line, 2017

Finite Size Corrections and Likelihood Ratio Fluctuations in the Spiked Wigner Model.
CoRR, 2017

Phase Transitions, Optimal Errors and Optimality of Message-Passing in Generalized Linear Models.
CoRR, 2017

A Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines.
CoRR, 2017

Constrained Low-rank Matrix Estimation: Phase Transitions, Approximate Message Passing and Applications.
CoRR, 2017

Information-theoretic thresholds from the cavity method.
Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing, 2017

Multi-layer generalized linear estimation.
Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017

Statistical and computational phase transitions in spiked tensor estimation.
Proceedings of the 2017 IEEE International Symposium on Information Theory, 2017

Streaming Bayesian inference: Theoretical limits and mini-batch approximate message-passing.
Proceedings of the 55th Annual Allerton Conference on Communication, 2017

2016
Phase Transitions and Sample Complexity in Bayes-Optimal Matrix Factorization.
IEEE Trans. Inf. Theory, 2016

Fast Phase Retrieval for High Dimensions: A Block-Based Approach.
IEEE Signal Process. Lett., 2016

Performance Limits for Noisy Multi-Measurement Vector Problems.
CoRR, 2016

Fast Randomized Semi-Supervised Clustering.
CoRR, 2016

Proceedings of the third "international Traveling Workshop on Interactions between Sparse models and Technology" (iTWIST'16).
CoRR, 2016

Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Inferring sparsity: Compressed sensing using generalized restricted Boltzmann machines.
Proceedings of the 2016 IEEE Information Theory Workshop, 2016

Mutual information in rank-one matrix estimation.
Proceedings of the 2016 IEEE Information Theory Workshop, 2016

Clustering from sparse pairwise measurements.
Proceedings of the IEEE International Symposium on Information Theory, 2016

Random projections through multiple optical scattering: Approximating Kernels at the speed of light.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Intensity-only optical compressive imaging using a multiply scattering material and a double phase retrieval approach.
Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Phase transitions and optimal algorithms in high-dimensional Gaussian mixture clustering.
Proceedings of the 54th Annual Allerton Conference on Communication, 2016

The mutual information in random linear estimation.
Proceedings of the 54th Annual Allerton Conference on Communication, 2016

2015
Statistical physics of inference: Thresholds and algorithms.
CoRR, 2015

Approximate Message Passing with Restricted Boltzmann Machine Priors.
CoRR, 2015

Intensity-only optical compressive imaging using a multiply scattering material : a double phase retrieval system.
CoRR, 2015

Training Restricted Boltzmann Machines via the Thouless-Anderson-Palmer Free Energy.
CoRR, 2015

Scampi: a robust approximate message-passing framework for compressive imaging.
CoRR, 2015

Matrix Completion from Fewer Entries: Spectral Detectability and Rank Estimation.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Training Restricted Boltzmann Machine via the Thouless-Anderson-Palmer free energy.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Spectral detection in the censored block model.
Proceedings of the IEEE International Symposium on Information Theory, 2015

Phase transitions in sparse PCA.
Proceedings of the IEEE International Symposium on Information Theory, 2015

Swept Approximate Message Passing for Sparse Estimation.
Proceedings of the 32nd International Conference on Machine Learning, 2015

Adaptive damping and mean removal for the generalized approximate message passing algorithm.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

Phase recovery from a Bayesian point of view: The variational approach.
Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

MMSE of probabilistic low-rank matrix estimation: Universality with respect to the output channel.
Proceedings of the 53rd Annual Allerton Conference on Communication, 2015

Spectral detection on sparse hypergraphs.
Proceedings of the 53rd Annual Allerton Conference on Communication, 2015

2014
Reweighted Belief Propagation and Quiet Planting for Random K-SAT.
J. Satisf. Boolean Model. Comput., 2014

Spectral density of the non-backtracking operator.
CoRR, 2014

Sparse Estimation with the Swept Approximated Message-Passing Algorithm.
CoRR, 2014

Spectral Clustering of graphs with the Bethe Hessian.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Variational free energies for compressed sensing.
Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014

On convergence of approximate message passing.
Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014

Replica analysis and approximate message passing decoder for superposition codes.
Proceedings of the 2014 IEEE International Symposium on Information Theory, Honolulu, HI, USA, June 29, 2014

2013
Spectral redemption: clustering sparse networks.
CoRR, 2013

The hard-core model on random graphs revisited.
CoRR, 2013

Compressed sensing and Approximate Message Passing with spatially-coupled Fourier and Hadamard matrices.
CoRR, 2013

Blind Calibration in Compressed Sensing using Message Passing Algorithms.
Proceedings of the Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013

Robust error correction for real-valued signals via message-passing decoding and spatial coupling.
Proceedings of the 2013 IEEE Information Theory Workshop, 2013

Phase diagram and approximate message passing for blind calibration and dictionary learning.
Proceedings of the 2013 IEEE International Symposium on Information Theory, 2013

Non-adaptive pooling strategies for detection of rare faulty items.
Proceedings of the IEEE International Conference on Communications, 2013

Compressed sensing under matrix uncertainty: Optimum thresholds and robust approximate message passing.
Proceedings of the IEEE International Conference on Acoustics, 2013

2012
Belief Propagation Reconstruction for Discrete Tomography
CoRR, 2012

The Quantum Adiabatic Algorithm applied to random optimization problems: the quantum spin glass perspective
CoRR, 2012

Model Selection for Degree-corrected Block Models
CoRR, 2012

Comparative Study for Inference of Hidden Classes in Stochastic Block Models
CoRR, 2012

Probabilistic Reconstruction in Compressed Sensing: Algorithms, Phase Diagrams, and Threshold Achieving Matrices
CoRR, 2012

Compressed sensing of approximately-sparse signals: Phase transitions and optimal reconstruction.
Proceedings of the 50th Annual Allerton Conference on Communication, 2012

2011
Quiet Planting in the Locked Constraint Satisfaction Problems.
SIAM J. Discret. Math., 2011

Statistical physics-based reconstruction in compressed sensing
CoRR, 2011

Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications
CoRR, 2011

Phase transition in the detection of modules in sparse networks
CoRR, 2011

2009
Quantum energy gaps and first-order mean-field-like transitions
CoRR, 2009

Hiding Quiet Solutions in Random Constraint Satisfaction Problems
CoRR, 2009

First-order transitions and the performance of quantum algorithms in random optimization problems.
CoRR, 2009

2007
Gibbs states and the set of solutions of random constraint satisfaction problems.
Proc. Natl. Acad. Sci. USA, 2007

A Landscape Analysis of Constraint Satisfaction Problems
CoRR, 2007

Phase Transitions and Computational Difficulty in Random Constraint Satisfaction Problems
CoRR, 2007

Constraint optimization and landscapes
CoRR, 2007

Phase Transitions in the Coloring of Random Graphs
CoRR, 2007

2004
Threshold values, stability analysis and high-q asymptotics for the coloring problem on random graphs
CoRR, 2004


  Loading...