10.6k citations
- Télécom ParisFR516 papers
- Centre National de la Recherche ScientifiqueFR356 papers
- ParisTechFR240 papers
- Université Paris-SaclayFR115 papers
- Université Paris-SudFR106 papers
- University of CambridgeGB95 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR94 papers
- Institut d'Astrophysique de ParisFR92 papers
- Sapienza University of RomeIT91 papers
- Imperial College LondonGB90 papers
- University of TorontoCA90 papers
- California Institute of TechnologyUS89 papers
61 papers · 1 filter
Exploiting Subgradient Sparsity in Max-Plus Neural Networks
Ikhlas Enaieh, Olivier Fercoq
Deep Neural Networks are powerful tools for solving machine learning problems, but their training often involves dense and costly parameter updates. In this work, we use a novel Ma…
Tight PAC-Bayesian Risk Certificates for Contrastive Learning
Anna Van Elst, Debarghya Ghoshdastidar
Contrastive representation learning is a modern paradigm for learning representations of unlabeled data via augmentations -- precisely, contrastive models learn to embed semantical…
Vector-Valued Least-Squares Regression under Output Regularity Assumptions
Luc Brogat-Motte, Alessandro Rudi, Céline Brouard +2
We propose and analyse a reduced-rank method for solving least-squares regression problems with infinite dimensional output. We derive learning bounds for our method, and study und…
Template-Based Graph Clustering
Mateus Riva, Florian Yger, Pietro Gori +2
We propose a novel graph clustering method guided by additional information on the underlying structure of the clusters (or communities). The problem is formulated as the matching…
UCSL : A Machine Learning Expectation-Maximization framework for Unsupervised Clustering driven by Supervised Learning
Robin Louiset, Pietro Gori, Benoit Dufumier +3
Subtype Discovery consists in finding interpretable and consistent sub-parts of a dataset, which are also relevant to a certain supervised task. From a mathematical point of view,…
Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections
Kimia Nadjahi, Alain Durmus, Pierre E. Jacob +2
The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications as an alternative to the Wasserstein distance and offers significant computational…