Robust algorithms for learning from modern data

Worst-Case Convergence Analysis of Inexact Gradient and Newton Methods Through Semidefinite Programming Performance Estimation

Autori: Etienne de Klerk; François Glineur; Adrien B. Taylor
Pubblicato in: SIAM Journal on Optimization, Numero 21, 2020, ISSN 1052-6234
Editore: Society for Industrial and Applied Mathematics
DOI: 10.1137/19m1281368

On the oracle complexity of smooth strongly convex minimization

Autori: Y. Drori; Adrien B. Taylor
Pubblicato in: Journal of Complexity, Numero 35, 2021, ISSN 1076-2787
Editore: John Wiley & Sons Inc.
DOI: 10.1016/j.jco.2021.101590

On the Effectiveness of Richardson Extrapolation in Data Science.

Autori: F. Bach.
Pubblicato in: SIAM Journal on Mathematics of Data Science, 2021, ISSN 2577-0187
Editore: SIAM
DOI: 10.1137/21m1397349

A note on approximate accelerated forward-backward methods with absolute and relative errors, and possibly strongly convex objectives

Autori: Mathieu Barré, Adrien Taylor & Francis Bach
Pubblicato in: Open Journal of Mathematical Optimization, 2022, ISSN 2777-5860
Editore: Mersenne
DOI: 10.5802/ojmo.12

Accelerated Gossip in Networks of Given Dimension using Jacobi Polynomial Iterations

Autori: Raphaël Berthier; Francis Bach; Pierre Gaillard
Pubblicato in: SIAM Journal on the Mathematics of Data Science, Numero 13, 2020, ISSN 2577-0187
Editore: SIAM
DOI: 10.1137/19m1244822

Efficient first-order methods for convex minimization: a constructive approach

Autori: Yoel Drori, Adrien B. Taylor
Pubblicato in: Mathematical Programming, 2018, ISSN 0025-5610
Editore: Springer Verlag
DOI: 10.1007/s10107-019-01410-2

Explicit Regularization of Stochastic Gradient Methods through Duality.

Autori: A. Raj, F. Bach.
Pubblicato in: Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
Editore: AISTATS

A Dimension-free Computational Upper-bound for Smooth Optimal Transport Estimation.

Autori: A. Vacher, B. Muzellec, A. Rudi, F. Bach, F.-X. Vialard.
Pubblicato in: Proceedings of the Conference on Learning Theory (COLT), 2021, 2021
Editore: COLT

Dual-Free Stochastic Decentralized Optimization with Variance Reduction.

Autori: H. Hendrikx, F. Bach, L. Massoulié.
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS), 2020
Editore: NeurIPS

Non-parametric Models for Non-negative Functions.

Autori: U. Marteau-Ferey, F. Bach, A. Rudi.
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS)., 2020
Editore: NeurIPS

Batch Normalization Provably Avoids Rank Collapse for Randomly Initialised Deep Networks.

Autori: H. Daneshmand, J. Kohler, F. Bach, T. Hofmann, A. Lucchi.
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS), 2020, 2020
Editore: NeurIPS

A Continuized View on Nesterov Acceleration for Stochastic Gradient Descent and Randomized Gossip

Autori: M. Even, R. Berthier, F. Bach, N. Flammarion, P. Gaillard, H. Hendrikx, L. Massoulié, A. Taylor.
Pubblicato in: Advances in Neural Information Processing Systems, 2021
Editore: NeurIPS

Learning with Differentiable Perturbed Optimizers

Autori: Berthet, Quentin; Blondel, Mathieu; Teboul, Olivier; Cuturi, Marco; Vert, Jean-Philippe; Bach, Francis
Pubblicato in: Advances in NeurIPS, Numero 39, 2020
Editore: NeurIPS

Relating Leverage Scores and Density using Regularized Christoffel Functions

Autori: Pauwels , Edouard; Bach , Francis; Vert , Jean-Philippe
Pubblicato in: Advances in NIPS, 2018
Editore: NIPS Foundation

Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes

Autori: Loucas Pillaud-Vivien, Alessandro Rudi, Francis Bach
Pubblicato in: Advances in Neural Information Processing Systems (NIPS), 2018
Editore: NIPS Foundation

On Fast Leverage Score Sampling and Optimal Learning

Autori: Rudi , Alessandro; Calandriello , Daniele; Carratino , Luigi; Rosasco , Lorenzo
Pubblicato in: Advances in NIPS, Numero 28, 2018
Editore: NIPS Foundation

Exponential convergence of testing error for stochastic gradient methods

Autori: Pillaud-Vivien, Loucas; Rudi, Alessandro; Bach, Francis
Pubblicato in: Proceedings of COLT, Numero 5, 2018
Editore: COLT

On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport

Autori: Chizat , Lenaic; Bach , Francis
Pubblicato in: Advances in NIPS, Numero 1, 2018
Editore: NIPS Foundation

Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions

Autori: Adrien Taylor, Francis Bach
Pubblicato in: Proceedings COLT, 2019
Editore: COLT

Affine Invariant Covariance Estimation for Heavy-Tailed Distributions

Autori: Ostrovskii, Dmitrii; Rudi, Alessandro
Pubblicato in: COLT 2019 - 32nd Annual Conference on Learning Theory, Numero 5, 2019
Editore: N/A

An accelerated decentralized stochastic proximal algorithm for finite Sums

Autori: Hadrien Hendrikx, Francis Bach, Laurent Massoulié
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS), 2019
Editore: N/A

On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport

Autori: Chizat , Lenaic; Bach , Francis
Pubblicato in: Advances in Neural Information Processing Systems (NIPS), Numero 2, 2018
Editore: N/A

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

Autori: Marteau-Ferey, Ulysse; Bach, Francis; Rudi, Alessandro
Pubblicato in: Advances in Neural Information Processing Systems (NeurIPS), 2019
Editore: N/A

On Lazy Training in Differentiable Programming

Autori: Chizat, Lenaic; Oyallon, Edouard; Bach, Francis
Pubblicato in: NeurIPS 2019 - 33rd Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada, Numero 15, 2019
Editore: N/A

Deep Equals Shallow for ReLU Networks in Kernel Regimes.

Autori: A. Bietti, F. Bach.
Pubblicato in: Proceedings of the International Conference on Learning Representations (ICLR), 2021
Editore: ICLR

Batch Normalization Orthogonalizes Representations in Deep Random Networks

Autori: H. Daneshmand, A. Joudaki, F. Bach.
Pubblicato in: Advances in NeurIPS, 2021
Editore: NeurIPS

Fast rates in structured prediction.

Autori: V. Cabannes, F. Bach, A. Rudi.
Pubblicato in: Proceedings of the Conference on Learning Theory (COLT), 2021
Editore: COLT

Finite-sample analysis of M-estimators using self-concordance

Autori: Dmitrii Ostrovskii; Francis Bach
Pubblicato in: Electronic Journal of Statistics, Numero 27, 2021, ISSN 1935-7524
Editore: Institute of Mathematical Statistics
DOI: 10.1214/20-ejs1780

Pubblicazioni

Condividi questa pagina

Scarica