Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Francis Bach

Francis Bach

PSL, DI-ENS, SIERRA

Disambiguation of weak supervision with exponential convergence rates


Feb 04, 2021
Vivien Cabannes, Francis Bach, Alessandro Rudi

* 22 pages; 6 figures 

  Access Paper or Ask Questions

Fast rates in structured prediction


Feb 01, 2021
Vivien Cabannes, Alessandro Rudi, Francis Bach

* 12 main pages, 2 main figures, 38 pages, 4 figures (with appendix) 

  Access Paper or Ask Questions

Finding Global Minima via Kernel Approximations


Dec 22, 2020
Alessandro Rudi, Ulysse Marteau-Ferey, Francis Bach


  Access Paper or Ask Questions

Deep Equals Shallow for ReLU Networks in Kernel Regimes


Oct 09, 2020
Alberto Bietti, Francis Bach


  Access Paper or Ask Questions

Variance-Reduced Methods for Machine Learning


Oct 02, 2020
Robert M. Gower, Mark Schmidt, Francis Bach, Peter Richtarik

* 16 pages, 7 figures, 1 table 

  Access Paper or Ask Questions

Non-parametric Models for Non-negative Functions


Jul 08, 2020
Ulysse Marteau-Ferey, Francis Bach, Alessandro Rudi


  Access Paper or Ask Questions

Consistent Structured Prediction with Max-Min Margin Markov Networks


Jul 02, 2020
Alex Nowak-Vila, Francis Bach, Alessandro Rudi


  Access Paper or Ask Questions

Structured and Localized Image Restoration


Jun 16, 2020
Thomas Eboli, Alex Nowak-Vila, Jian Sun, Francis Bach, Jean Ponce, Alessandro Rudi


  Access Paper or Ask Questions

Tight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model


Jun 15, 2020
Raphaël Berthier, Francis Bach, Pierre Gaillard


  Access Paper or Ask Questions

ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing


Jun 08, 2020
Théo Ryffel, David Pointcheval, Francis Bach


  Access Paper or Ask Questions

Explicit Regularization of Stochastic Gradient Methods through Duality


Mar 30, 2020
Anant Raj, Francis Bach


  Access Paper or Ask Questions

Theoretical Understanding of Batch-normalization: A Markov Chain Perspective


Mar 09, 2020
Hadi Daneshmand, Jonas Kohler, Francis Bach, Thomas Hofmann, Aurelien Lucchi


  Access Paper or Ask Questions

On the Convergence of Adam and Adagrad


Mar 05, 2020
Alexandre DĂ©fossez, LĂ©on Bottou, Francis Bach, Nicolas Usunier

* 19 pages, 0 figures, preprint version 

  Access Paper or Ask Questions

Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss


Mar 04, 2020
Lenaic Chizat, Francis Bach


  Access Paper or Ask Questions

Structured Prediction with Partial Labelling through the Infimum Loss


Mar 02, 2020
Vivien Cabannes, Alessandro Rudi, Francis Bach

* 8 pages for main paper, 27 with main paper, 13 figures, 3 tables 

  Access Paper or Ask Questions

Safe Screening for the Generalized Conditional Gradient Method


Feb 22, 2020
Yifan Sun, Francis Bach


  Access Paper or Ask Questions

Stochastic Optimization for Regularized Wasserstein Estimators


Feb 20, 2020
Marin Ballu, Quentin Berthet, Francis Bach


  Access Paper or Ask Questions

Learning with Differentiable Perturbed Optimizers


Feb 20, 2020
Quentin Berthet, Mathieu Blondel, Olivier Teboul, Marco Cuturi, Jean-Philippe Vert, Francis Bach


  Access Paper or Ask Questions

On the Effectiveness of Richardson Extrapolation in Machine Learning


Feb 07, 2020
Francis Bach


  Access Paper or Ask Questions

Music Source Separation in the Waveform Domain


Nov 27, 2019
Alexandre DĂ©fossez, Nicolas Usunier, LĂ©on Bottou, Francis Bach


  Access Paper or Ask Questions

UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization


Oct 30, 2019
Ali Kavis, Kfir Y. Levy, Francis Bach, Volkan Cevher

* NeurIPS 2019 

  Access Paper or Ask Questions

Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed


Sep 03, 2019
Alexandre DĂ©fossez, Nicolas Usunier, LĂ©on Bottou, Francis Bach


  Access Paper or Ask Questions

Towards closing the gap between the theory and practice of SVRG


Jul 31, 2019
Othmane Sebbouh, Nidham Gazagnadou, Samy Jelassi, Francis Bach, Robert M. Gower

* 39 pages, 23 figures 

  Access Paper or Ask Questions

Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant Losses


Jul 03, 2019
Ulysse Marteau-Ferey, Francis Bach, Alessandro Rudi


  Access Paper or Ask Questions

Max-Plus Matching Pursuit for Deterministic Markov Decision Processes


Jun 20, 2019
Francis Bach


  Access Paper or Ask Questions

Partially Encrypted Machine Learning using Functional Encryption


May 29, 2019
Theo Ryffel, Edouard Dufour-Sans, Romain Gay, Francis Bach, David Pointcheval


  Access Paper or Ask Questions