Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDFlorent Krzakala
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
[j15]Antoine Baker, Florent Krzakala, Benjamin Aubin, Lenka Zdeborová:
Tree-AMP: Compositional Inference with Tree Approximate Message Passing. J. Mach. Learn. Res. 24: 57:1-57:89 (2023)- [j14]Sebastian Goldt
, Florent Krzakala, Lenka Zdeborová, Nicolas Brunel:
Bayesian reconstruction of memories stored in neural networks from their connectivity. PLoS Comput. Biol. 19(1) (2023) - [j13]Cédric Gerbelot, Alia Abbara, Florent Krzakala:
Asymptotic Errors for Teacher-Student Convex Generalized Linear Models (Or: How to Prove Kabashima's Replica Formula). IEEE Trans. Inf. Theory 69(3): 1824-1852 (2023) - [c77]Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
On double-descent in uncertainty quantification in overparametrized models. AISTATS 2023: 7089-7125 - [c76]Luca Arnaboldi, Ludovic Stephan, Florent Krzakala, Bruno Loureiro:
From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks. COLT 2023: 1199-1227 - [c75]Hugo Cui, Florent Krzakala, Lenka Zdeborová:
Bayes-optimal Learning of Deep Random Networks of Extensive-width. ICML 2023: 6468-6521 - [c74]Luca Pesce, Florent Krzakala, Bruno Loureiro, Ludovic Stephan:
Are Gaussian Data All You Need? The Extents and Limits of Universality in High-Dimensional Generalized Linear Estimation. ICML 2023: 27680-27708 - [c73]D. Barbier, Carlo Lucibello, Luca Saglietti, Florent Krzakala, Lenka Zdeborová:
Compressed sensing with ℓ0-norm: statistical physics analysis & algorithms for signal recovery. ITW 2023: 323-328 - [c72]Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Expectation consistency for calibration of neural networks. UAI 2023: 443-453 - [i141]Hugo Cui, Florent Krzakala, Lenka Zdeborová:
Optimal Learning of Deep Random Networks of Extensive-width. CoRR abs/2302.00375 (2023) - [i140]Luca Arnaboldi, Ludovic Stephan, Florent Krzakala, Bruno Loureiro:
From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks. CoRR abs/2302.05882 (2023) - [i139]Aleksandr Pak, Justin Ko, Florent Krzakala:
Optimal Algorithms for the Inhomogeneous Spiked Wigner Model. CoRR abs/2302.06665 (2023) - [i138]Luca Pesce, Florent Krzakala, Bruno Loureiro, Ludovic Stephan:
Are Gaussian data all you need? Extents and limits of universality in high-dimensional generalized linear estimation. CoRR abs/2302.08923 (2023) - [i137]Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Expectation consistency for calibration of neural networks. CoRR abs/2303.02644 (2023) - [i136]Vittorio Erba, Florent Krzakala, Rodrigo Pérez, Lenka Zdeborová:
Statistical mechanics of the maximum-average submatrix problem. CoRR abs/2303.05237 (2023) - [i135]D. Barbier, Carlo Lucibello, Luca Saglietti, Florent Krzakala, Lenka Zdeborová:
Compressed sensing with l0-norm: statistical physics analysis and algorithms for signal recovery. CoRR abs/2304.12127 (2023) - [i134]Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan:
Learning Two-Layer Neural Networks, One (Giant) Step at a Time. CoRR abs/2305.18270 (2023) - [i133]Luca Arnaboldi, Florent Krzakala, Bruno Loureiro, Ludovic Stephan:
Escaping mediocrity: how two-layer networks learn hard single-index models with SGD. CoRR abs/2305.18502 (2023) - [i132]Matteo Vilucchio, Emanuele Troiani, Vittorio Erba, Florent Krzakala:
Asymptotic Characterisation of Robust Empirical Risk Minimisation Performance in the Presence of Outliers. CoRR abs/2305.18974 (2023) - [i131]Davide Ghio, Yatin Dandi, Florent Krzakala, Lenka Zdeborová:
Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective. CoRR abs/2308.14085 (2023) - [i130]Hugo Cui, Florent Krzakala, Eric Vanden-Eijnden, Lenka Zdeborová:
Analysis of learning a flow-based generative model from limited sample complexity. CoRR abs/2310.03575 (2023) - 2022
- [c71]Alessandro Cappelli, Ruben Ohana, Julien Launay, Laurent Meunier, Iacopo Poli, Florent Krzakala:
Adversarial Robustness by Design Through Analog Computing And Synthetic Gradients. ICASSP 2022: 3493-3497 - [c70]Bruno Loureiro, Cédric Gerbelot, Maria Refinetti, Gabriele Sicuro, Florent Krzakala:
Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension. ICML 2022: 14283-14314 - [c69]Ali Bereyhi, Bruno Loureiro, Florent Krzakala, Ralf R. Müller, Hermann Schulz-Baldes:
Secure Coding via Gaussian Random Fields. ISIT 2022: 1241-1246 - [c68]Emanuele Troiani, Vittorio Erba, Florent Krzakala, Antoine Maillard, Lenka Zdeborová:
Optimal denoising of rotationally invariant rectangular matrices. MSML 2022: 97-112 - [c67]Max Daniels, Cédric Gerbelot, Florent Krzakala, Lenka Zdeborová:
Multi-layer State Evolution Under Random Convolutional Design. NeurIPS 2022 - [c66]Luca Pesce, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap. NeurIPS 2022 - [c65]Rodrigo Veiga, Ludovic Stephan, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks. NeurIPS 2022 - [i129]Ali Bereyhi, Bruno Loureiro, Florent Krzakala, Ralf R. Müller, Hermann Schulz-Baldes:
Bayesian Inference with Nonlinear Generative Models: Comments on Secure Learning. CoRR abs/2201.09986 (2022) - [i128]Hugo Cui, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Error Rates for Kernel Classification under Source and Capacity Conditions. CoRR abs/2201.12655 (2022) - [i127]Bruno Loureiro, Cédric Gerbelot, Maria Refinetti, Gabriele Sicuro, Florent Krzakala:
Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension. CoRR abs/2201.13383 (2022) - [i126]Rodrigo Veiga, Ludovic Stephan, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks. CoRR abs/2202.00293 (2022) - [i125]Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Theoretical characterization of uncertainty in high-dimensional linear classification. CoRR abs/2202.03295 (2022) - [i124]Emanuele Troiani, Vittorio Erba, Florent Krzakala, Antoine Maillard, Lenka Zdeborová:
Optimal denoising of rotationally invariant rectangular matrices. CoRR abs/2203.07752 (2022) - [i123]Ali Bereyhi, Bruno Loureiro, Florent Krzakala, Ralf R. Müller, Hermann Schulz-Baldes:
Secure Coding via Gaussian Random Fields. CoRR abs/2205.08782 (2022) - [i122]Federica Gerace, Florent Krzakala, Bruno Loureiro, Ludovic Stephan, Lenka Zdeborová:
Gaussian Universality of Linear Classifiers with Random Labels in High-Dimension. CoRR abs/2205.13303 (2022) - [i121]Max Daniels, Cédric Gerbelot, Florent Krzakala, Lenka Zdeborová:
Multi-layer State Evolution Under Random Convolutional Design. CoRR abs/2205.13503 (2022) - [i120]Luca Pesce, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Subspace clustering in high-dimensions: Phase transitions \& Statistical-to-Computational gap. CoRR abs/2205.13527 (2022) - [i119]Cédric Gerbelot, Emanuele Troiani, Francesca Mignacco, Florent Krzakala, Lenka Zdeborová:
Rigorous dynamical mean field theory for stochastic gradient descent methods. CoRR abs/2210.06591 (2022) - [i118]Lucas Clarté, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
A study of uncertainty quantification in overparametrized high-dimensional models. CoRR abs/2210.12760 (2022) - 2021
- [j12]Benjamin Aubin, Bruno Loureiro, Antoine Maillard, Florent Krzakala, Lenka Zdeborová:
The Spiked Matrix Model With Generative Priors. IEEE Trans. Inf. Theory 67(2): 1156-1181 (2021) - [c64]Charles Brossollet, Alessandro Cappelli, Igor Carron, Charidimos Chaintoutis, Amélie Chatelain, Laurent Daudet, Sylvain Gigan, Daniel Hesslow, Florent Krzakala, Julien Launay, Safa Mokaadi, Fabien Moreau, Kilian Müller, Ruben Ohana, Gustave Pariente, Iacopo Poli, Giuseppe Luca Tommasone:
LightOn Optical Processing Unit : Scaling-up AI and HPC with a Non von Neumann co-processor. HCS 2021: 1-11 - [c63]Maria Refinetti, Sebastian Goldt, Florent Krzakala, Lenka Zdeborová:
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed. ICML 2021: 8936-8947 - [c62]Sebastian Goldt, Bruno Loureiro, Galen Reeves, Florent Krzakala, Marc Mézard, Lenka Zdeborová:
The Gaussian equivalence of generative models for learning with shallow neural networks. MSML 2021: 426-471 - [c61]Antoine Maillard, Florent Krzakala, Yue M. Lu, Lenka Zdeborová:
Construction of optimal spectral methods in phase retrieval. MSML 2021: 693-720 - [c60]Hugo Cui, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime. NeurIPS 2021: 10131-10143 - [c59]Bruno Loureiro, Gabriele Sicuro, Cédric Gerbelot, Alessandro Pacco, Florent Krzakala, Lenka Zdeborová:
Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions. NeurIPS 2021: 10144-10157 - [c58]Bruno Loureiro, Cédric Gerbelot, Hugo Cui, Sebastian Goldt, Florent Krzakala, Marc Mézard, Lenka Zdeborová:
Learning curves of generic features maps for realistic datasets with a teacher-student model. NeurIPS 2021: 18137-18151 - [i117]Alessandro Cappelli, Ruben Ohana, Julien Launay, Laurent Meunier, Iacopo Poli, Florent Krzakala:
Adversarial Robustness by Design through Analog Computing and Synthetic Gradients. CoRR abs/2101.02115 (2021) - [i116]Bruno Loureiro, Cédric Gerbelot, Hugo Cui, Sebastian Goldt, Florent Krzakala, Marc Mézard, Lenka Zdeborová:
Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model. CoRR abs/2102.08127 (2021) - [i115]Maria Refinetti, Sebastian Goldt, Florent Krzakala, Lenka Zdeborová:
Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed. CoRR abs/2102.11742 (2021) - [i114]Hugo Cui, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime. CoRR abs/2105.15004 (2021) - [i113]Bruno Loureiro, Gabriele Sicuro, Cédric Gerbelot, Alessandro Pacco, Florent Krzakala, Lenka Zdeborová:
Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions. CoRR abs/2106.03791 (2021) - [i112]Charles Brossollet, Alessandro Cappelli, Igor Carron, Charidimos Chaintoutis, Amélie Chatelain, Laurent Daudet, Sylvain Gigan, Daniel Hesslow, Florent Krzakala, Julien Launay, Safa Mokaadi, Fabien Moreau, Kilian Müller, Ruben Ohana, Gustave Pariente, Iacopo Poli, Giuseppe Luca Tommasone:
LightOn Optical Processing Unit: Scaling-up AI and HPC with a Non von Neumann co-processor. CoRR abs/2107.11814 (2021) - [i111]Antoine Maillard, Florent Krzakala, Marc Mézard, Lenka Zdeborová:
Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising. CoRR abs/2110.08775 (2021) - 2020
- [j11]Jean Barbier, Nicolas Macris, Mohamad Dia, Florent Krzakala:
Mutual Information and Optimality of Approximate Message-Passing in Random Linear Estimation. IEEE Trans. Inf. Theory 66(7): 4270-4303 (2020) - [c57]Cédric Gerbelot, Alia Abbara, Florent Krzakala:
Asymptotic Errors for High-Dimensional Convex Penalized Linear Regression beyond Gaussian Matrices. COLT 2020: 1682-1713 - [c56]Ruben Ohana, Jonas Wacker, Jonathan Dong, Sébastien Marmin, Florent Krzakala, Maurizio Filippone, Laurent Daudet:
Kernel Computations from Large-Scale Random Features Obtained by Optical Processing Units. ICASSP 2020: 9294-9298 - [c55]Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli, Florent Krzakala:
Double Trouble in Double Descent: Bias and Variance(s) in the Lazy Regime. ICML 2020: 2280-2290 - [c54]Federica Gerace, Bruno Loureiro, Florent Krzakala, Marc Mézard, Lenka Zdeborová:
Generalisation error in learning with random features and the hidden manifold model. ICML 2020: 3452-3462 - [c53]Francesca Mignacco, Florent Krzakala, Yue Lu, Pierfrancesco Urbani, Lenka Zdeborová:
The Role of Regularization in Classification of High-dimensional Noisy Gaussian Mixture. ICML 2020: 6874-6883 - [c52]Alia Abbara, Benjamin Aubin, Florent Krzakala, Lenka Zdeborová:
Rademacher complexity and spin glasses: A link between the replica and statistical theories of learning. MSML 2020: 27-54 - [c51]Benjamin Aubin, Bruno Loureiro, Antoine Baker, Florent Krzakala, Lenka Zdeborová:
Exact asymptotics for phase retrieval and compressed sensing with random generative priors. MSML 2020: 55-73 - [c50]Benjamin Aubin, Florent Krzakala, Yue M. Lu, Lenka Zdeborová:
Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization. NeurIPS 2020 - [c49]Jonathan Dong, Ruben Ohana, Mushegh Rafayelyan, Florent Krzakala:
Reservoir Computing meets Recurrent Kernels and Structured Transforms. NeurIPS 2020 - [c48]Julien Launay, Iacopo Poli, François Boniface, Florent Krzakala:
Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures. NeurIPS 2020 - [c47]Antoine Maillard, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Phase retrieval in high dimensions: Statistical and computational phase transitions. NeurIPS 2020 - [c46]Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová:
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval. NeurIPS 2020 - [c45]Francesca Mignacco, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová:
Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification. NeurIPS 2020 - [i110]Mushegh Rafayelyan, Jonathan Dong, Yongqi Tan, Florent Krzakala, Sylvain Gigan:
Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction. CoRR abs/2001.09131 (2020) - [i109]Federica Gerace, Bruno Loureiro, Florent Krzakala, Marc Mézard, Lenka Zdeborová:
Generalisation error in learning with random features and the hidden manifold model. CoRR abs/2002.09339 (2020) - [i108]Francesca Mignacco, Florent Krzakala, Yue M. Lu, Lenka Zdeborová:
The role of regularization in classification of high-dimensional noisy Gaussian mixture. CoRR abs/2002.11544 (2020) - [i107]Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli, Florent Krzakala:
Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime. CoRR abs/2003.01054 (2020) - [i106]Antoine Baker, Benjamin Aubin, Florent Krzakala, Lenka Zdeborová:
TRAMP: Compositional Inference with TRee Approximate Message Passing. CoRR abs/2004.01571 (2020) - [i105]Julien Launay, Iacopo Poli, Kilian Müller, Igor Carron, Laurent Daudet, Florent Krzakala, Sylvain Gigan:
Light-in-the-loop: using a photonics co-processor for scalable training of neural networks. CoRR abs/2006.01475 (2020) - [i104]Antoine Maillard, Bruno Loureiro, Florent Krzakala, Lenka Zdeborová:
Phase retrieval in high dimensions: Statistical and computational phase transitions. CoRR abs/2006.05228 (2020) - [i103]Francesca Mignacco, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová:
Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification. CoRR abs/2006.06098 (2020) - [i102]Benjamin Aubin, Florent Krzakala, Yue M. Lu, Lenka Zdeborová:
Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization. CoRR abs/2006.06560 (2020) - [i101]Cédric Gerbelot, Alia Abbara, Florent Krzakala:
Asymptotic Errors for Teacher-Student Convex Generalized Linear Models (or : How to Prove Kabashima's Replica Formula). CoRR abs/2006.06581 (2020) - [i100]Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová:
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval. CoRR abs/2006.06997 (2020) - [i99]Jonathan Dong, Ruben Ohana, Mushegh Rafayelyan, Florent Krzakala:
Reservoir Computing meets Recurrent Kernels and Structured Transforms. CoRR abs/2006.07310 (2020) - [i98]Julien Launay, Iacopo Poli, François Boniface, Florent Krzakala:
Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures. CoRR abs/2006.12878 (2020) - [i97]Sebastian Goldt, Galen Reeves, Marc Mézard, Florent Krzakala, Lenka Zdeborová:
The Gaussian equivalence of generative models for learning with two-layer neural networks. CoRR abs/2006.14709 (2020) - [i96]Antoine Baker, Indaco Biazzo, Alfredo Braunstein, Giovanni Catania, Luca Dall'Asta, Alessandro Ingrosso, Florent Krzakala, Fabio Mazza, Marc Mézard, Anna Paola Muntoni, Maria Refinetti, Stefano Sarao Mannelli, Lenka Zdeborová:
Epidemic mitigation by statistical inference from contact tracing data. CoRR abs/2009.09422 (2020) - [i95]Antoine Maillard, Florent Krzakala, Yue M. Lu, Lenka Zdeborová:
Construction of optimal spectral methods in phase retrieval. CoRR abs/2012.04524 (2020) - [i94]Julien Launay, Iacopo Poli, Kilian Müller, Gustave Pariente, Igor Carron, Laurent Daudet, Florent Krzakala, Sylvain Gigan:
Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment. CoRR abs/2012.06373 (2020)
2010 – 2019
- 2019
- [j10]Ahmed El Alaoui, Aaditya Ramdas, Florent Krzakala, Lenka Zdeborová, Michael I. Jordan:
Decoding from Pooled Data: Sharp Information-Theoretic Bounds. SIAM J. Math. Data Sci. 1(1): 161-188 (2019) - [j9]Ahmed El Alaoui, Aaditya Ramdas, Florent Krzakala, Lenka Zdeborová, Michael I. Jordan:
Decoding From Pooled Data: Phase Transitions of Message Passing. IEEE Trans. Inf. Theory 65(1): 572-585 (2019) - [c44]Marylou Gabrié, Jean Barbier, Florent Krzakala, Lenka Zdeborová:
Blind Calibration for Sparse Regression: A State Evolution Analysis. CAMSAP 2019: 649-653 - [c43]Jonathan Dong, Florent Krzakala, Sylvain Gigan:
Spectral Method for Multiplexed Phase Retrieval and Application in Optical Imaging in Complex Media. ICASSP 2019: 4963-4967 - [c42]Stefano Sarao Mannelli, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová:
Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models. ICML 2019: 4333-4342 - [c41]Sebastian Goldt, Madhu Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová:
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup. NeurIPS 2019: 6979-6989 - [c40]Benjamin Aubin, Bruno Loureiro, Antoine Maillard, Florent Krzakala, Lenka Zdeborová:
The spiked matrix model with generative priors. NeurIPS 2019: 8364-8375 - [c39]Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Lenka Zdeborová:
Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models. NeurIPS 2019: 8676-8686 - [i93]Sebastian Goldt, Madhu S. Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová:
Generalisation dynamics of online learning in over-parameterised neural networks. CoRR abs/1901.09085 (2019) - [i92]Stefano Sarao Mannelli, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová:
Passed & Spurious: analysing descent algorithms and local minima in spiked matrix-tensor model. CoRR abs/1902.00139 (2019) - [i91]Benjamin Aubin, Bruno Loureiro, Antoine Maillard, Florent Krzakala, Lenka Zdeborová:
The spiked matrix model with generative priors. CoRR abs/1905.12385 (2019) - [i90]Julien Launay, Iacopo Poli, Florent Krzakala:
Principled Training of Neural Networks with Direct Feedback Alignment. CoRR abs/1906.04554 (2019) - [i89]Alia Abbara, Antoine Baker, Florent Krzakala, Lenka Zdeborová:
On the Universality of Noiseless Linear Estimation with Respect to the Measurement Matrix. CoRR abs/1906.04735 (2019) - [i88]Antoine Maillard, Laura Foini, Alejandro Lage Castellanos, Florent Krzakala, Marc Mézard, Lenka Zdeborová:
High-temperature Expansions and Message Passing Algorithms. CoRR abs/1906.08479 (2019) - [i87]Sebastian Goldt, Madhu S. Advani, Andrew M. Saxe, Florent Krzakala, Lenka Zdeborová:
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup. CoRR abs/1906.08632 (2019) - [i86]Jonathan Dong, Mushegh Rafayelyan, Florent Krzakala, Sylvain Gigan:
Optical Reservoir Computing using multiple light scattering for chaotic systems prediction. CoRR abs/1907.00657 (2019) - [i85]Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Lenka Zdeborová:
Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model. CoRR abs/1907.08226 (2019) - [i84]Sebastian Goldt, Marc Mézard, Florent Krzakala, Lenka Zdeborová:
Modelling the influence of data structure on learning in neural networks. CoRR abs/1909.11500 (2019) - [i83]Marylou Gabrié, Jean Barbier, Florent Krzakala, Lenka Zdeborová:
Blind calibration for compressed sensing: State evolution and an online algorithm. CoRR abs/1910.00285 (2019) - [i82]Ruben Ohana, Jonas Wacker, Jonathan Dong, Sébastien Marmin, Florent Krzakala, Maurizio Filippone, Laurent Daudet:
Kernel computations from large-scale random features obtained by Optical Processing Units. CoRR abs/1910.09880 (2019) - [i81]Benjamin Aubin, Bruno Loureiro, Antoine Baker, Florent Krzakala, Lenka Zdeborová:
Exact asymptotics for phase retrieval and compressed sensing with random generative priors. CoRR abs/1912.02008 (2019) - [i80]Alia Abbara, Benjamin Aubin, Florent Krzakala, Lenka Zdeborová:
Rademacher complexity and spin glasses: A link between the replica and statistical theories of learning. CoRR abs/1912.02729 (2019) - 2018
- [c38]Jean Barbier, Florent Krzakala, Nicolas Macris, Léo Miolane, Lenka Zdeborová:
Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models. COLT 2018: 728-731 - [c37]Jean Barbier, Nicolas Macris, Antoine Maillard, Florent Krzakala:
The Mutual Information in Random Linear Estimation Beyond i.i.d. Matrices. ISIT 2018: 1390-1394 - [c36]Ahmed El Alaoui, Florent Krzakala:
Estimation in the Spiked Wigner Model: A Short Proof of the Replica Formula. ISIT 2018: 1874-1878 - [c35]Marylou Gabrié, Andre Manoel, Clément Luneau, Jean Barbier, Nicolas Macris, Florent Krzakala, Lenka Zdeborová:
Entropy and mutual information in models of deep neural networks. NeurIPS 2018: 1826-1836 - [c34]Benjamin Aubin, Antoine Maillard, Jean Barbier, Florent Krzakala, Nicolas Macris, Lenka Zdeborová:
The committee machine: Computational to statistical gaps in learning a two-layers neural network. NeurIPS 2018: 3227-3238 - [c33]