Recherche - ANR - Agence nationale de la recherche Accéder directement au contenu

Filtrer vos résultats

45 résultats
Image document

Expressive Losses for Verified Robustness via Convex Combinations

Alessandro De Palma , Rudy Bunel , Krishnamurthy Dvijotham , M Pawan Kumar , Robert Stanforth , et al.
ICLR 2024 - International Conference on Learning Representations, May 2024, Vienna, Austria
Communication dans un congrès hal-04511820v1

Concentrated Differential Privacy for Bandits

Achraf Azize , Debabrota Basu
2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), IEEE, Apr 2024, Toronto, Canada. pp.78-109, ⟨10.1109/SaTML59370.2024.00013⟩
Communication dans un congrès hal-04611650v1

Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer

Hannes Eriksson , Tommy Tram , Debabrota Basu , Mina Alibeigi , Christos Dimitrakakis
23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS), May 2024, Auckland, New Zealand. pp.516-524, ⟨10.5555/3635637.3662902⟩
Communication dans un congrès hal-04260795v1
Image document

A geometric decomposition of finite games: Convergence vs. recurrence under exponential weights

Davide Legacci , Panayotis Mertikopoulos , Bary Pradelski
ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria. pp.1-49
Communication dans un congrès hal-04629310v1
Image document

The Computational Complexity of Finding Second-Order Stationary Points

Andreas Kontogiannis , Vasilis Pollatos , Sotiris Kanellopoulos , Panayotis Mertikopoulos , Aris Pagourtzis , et al.
ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria. pp.1-35
Communication dans un congrès hal-04629307v1
Image document

A PAC-Bayesian Link Between Generalisation and Flat Minima

Maxime Haddouche , Paul Viallard , Umut Şimşekli , Benjamin Guedj
2024
Pré-publication, Document de travail hal-04455639v1

Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows

Sibylle Marcotte , Rémi Gribonval , Gabriel Peyré
41st International Conference on Machine Learning, Jul 2024, Vienna, Austria
Communication dans un congrès hal-04590932v1
Image document

Reconstructing discrete measures from projections. Consequences on the empirical Sliced Wasserstein Distance

Eloi Tanguy , Rémi Flamary , Julie Delon
2024
Pré-publication, Document de travail hal-04232769v2
Image document

Properties of Discrete Sliced Wasserstein Losses

Eloi Tanguy , Rémi Flamary , Julie Delon
2024
Pré-publication, Document de travail hal-04232766v2
Image document

What is the long-run distribution of stochastic gradient descent? A large deviations analysis

Waïss Azizian , Franck Iutzeler , Jérôme Malick , Panayotis Mertikopoulos
ICML 2024 - 41st International Conference on Machine Learning, Jul 2024, Vienna, Austria. pp.1-70
Communication dans un congrès hal-04629305v1
Image document

Heavy Ball Momentum for Non-Strongly Convex Optimization

Jean-François Aujol , Charles Dossal , Hippolyte Labarrière , Aude Rondepierre
2024
Pré-publication, Document de travail hal-04500652v1
Image document

Bandits Corrupted by Nature: Lower Bounds on Regret and Robust Optimistic Algorithms

Timothée Mathieu , Debabrota Basu , Odalric-Ambrym Maillard
Transactions on Machine Learning Research Journal, 2024
Article dans une revue hal-04615733v1
Image document

Open Problem: What is the Complexity of Joint Differential Privacy in Linear Contextual Bandits?

Achraf Azize , Debabrota Basu
Proceedings of Thirty Seventh Conference on Learning Theory, Jul 2024, Edmonton (Alberta), Canada
Communication dans un congrès hal-04621903v1
Image document

Tamed Langevin sampling under weaker conditions

Iosif Lytras , Panayotis Mertikopoulos
2024
Pré-publication, Document de travail hal-04629313v1
Image document

Sliced-Wasserstein Estimation with Spherical Harmonics as Control Variates

Rémi Leluc , Aymeric Dieuleveut , François Portier , Johan Segers , Aigerim Zhuman
2024
Pré-publication, Document de travail hal-04438124v1
Image document

Make Inference Faster: Efficient GPU Memory Management for Butterfly Sparse Matrix Multiplication

Antoine Gonon , Léon Zheng , Pascal Carrivain , Quoc-Tung Le
2024
Pré-publication, Document de travail hal-04584450v2
Image document

Joint structure-texture low dimensional modeling for image decomposition with a plug and play framework

Antoine Guennec , Jean-François Aujol , Yann Traonmilin
2024
Pré-publication, Document de travail hal-04648963v1
Image document

Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm

Batiste Le Bars , Aurélien Bellet , Marc Tommasi , Kevin Scaman , Giovanni Neglia
ICML 2024 - The Forty-first International Conference on Machine Learning, Jul 2024, Vienne, Austria
Communication dans un congrès hal-04611418v1
Image document

Monotonicity and the Precision of Program Analysis

Marco Campion , Mila Dalla Preda , Roberto Giacobazzi , Caterina Urban
Proceedings of the ACM on Programming Languages, 2024, 8 (POPL), pp.1629-1662. ⟨10.1145/3632897⟩
Article dans une revue hal-04423578v1
Image document

LOCOST: State-Space Models for Long Document Abstractive Summarization

Florian Le Bronnec , Song Duong , Mathieu Ravaut , Alexandre Allauzen , Nancy F. Chen , et al.
European Chapter of the Association for Computational Linguistics (EACL), Mar 2024, St. Julian’s, Malta
Communication dans un congrès hal-04438465v1
Image document

Accelerating the convergence of Newton's method for nonlinear elliptic PDEs using Fourier neural operators

Joubine Aghili , Romain Hild , Victor Michel-Dansac , Vincent Vigon , Emmanuel Franck
2024
Pré-publication, Document de travail hal-04440076v2
Image document

Discrete-to-continuous crystalline curvature flows

Antonin Chambolle , Daniele de Gennaro , Massimiliano Morini
2024
Pré-publication, Document de travail hal-04500307v2
Image document

Promouvoir des modèles d’intelligence artificielle frugale pour et par les politiques publiques

Maxime Amisse , Mélissa Faur , Lucie Gonard , André Orcesi
Ecole des Ponts Paris Tech, Paris-France. 2024
Rapport hal-04510171v1
Image document

Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses

Eloi Tanguy
2024
Pré-publication, Document de travail hal-04232792v2
Image document

Inclusion and estimates for the jumps of minimizers in variational denoising

Antonin Chambolle , Michał Łasica
2023
Pré-publication, Document de travail hal-04323807v1
Image document

A Stochastic Rounding-Enabled Low-Precision Floating-Point MAC for DNN Training

Sami Ben Ali , Silviu-Ioan Filip , Olivier Sentieys
DATE 2024 - 27th IEEE/ACM Design, Automation and Test in Europe, Mar 2024, Valencia, Spain. pp.1-6
Communication dans un congrès hal-04380270v2
Image document

Investigating on Gradient Regularization for Testing Neural Networks

Nicolo Bellarmino , Alberto Bosio , Riccardo Cantoro , Annachiara Ruospo , Ernesto Sanchez , et al.
LOD 2024 : 10th International Conference on machine Learning, Optimization and Data science, Sep 2024, Riva de Sole, Italy
Communication dans un congrès hal-04604264v1
Image document

Study of the behaviour of Nesterov Accelerated Gradient in a non convex setting: the strongly quasar convex case

J Hermant , J.-F Aujol , C Dossal , A Rondepierre
2024
Pré-publication, Document de travail hal-04589853v1

On the Impact of Output Perturbation on Fairness in Binary Linear Classification

Vitalii Emelianov , Michaël Perrot
2024
Pré-publication, Document de travail hal-04440982v1

Tighter Generalisation Bounds via Interpolation

Paul Viallard , Maxime Haddouche , Umut Şimşekli , Benjamin Guedj
2024
Pré-publication, Document de travail hal-04456925v1