466 citations
- Université Grenoble AlpesFR107 papers
- Centre National de la Recherche ScientifiqueFR59 papers
- Institut polytechnique de GrenobleFR40 papers
- Institut national de recherche en sciences et technologies du numériqueFR31 papers
- Centre Inria de l'Université Grenoble AlpesFR26 papers
- GIPSA-LabFR15 papers
- Institute of MiningRU8 papers
- Université Paris CitéFR7 papers
- Institut de Recherche en Informatique de ToulouseFR6 papers
- Institut des langues et cultures d'Europe, Amérique, Afrique, Asie et AustralieFR6 papers
- Université Savoie Mont BlancFR6 papers
- Université Toulouse III - Paul SabatierFR6 papers
16 papers · 1 filter
A Unified Contrastive Loss for Self-Training
Aurelien Gauffre, Julien Horvat, Massih-Reza Amini
Self-training methods have proven to be effective in exploiting abundant unlabeled data in semi-supervised learning, particularly when labeled data is scarce. While many of these a…
An Analysis of Linear Complexity Attention Substitutes with BEST-RQ
Ryan Whetten, Titouan Parcollet, Adel Moumen +2
Self-Supervised Learning (SSL) has proven to be effective in various domains, including speech processing. However, SSL is computationally and memory expensive. This is in part due…
Pool-Based Active Learning with Proper Topological Regions
Lies Hadjadj, Emilie Devijver, Remi Molinier +1
Machine learning methods usually rely on large sample size to have good performance, while it is difficult to provide labeled set in many applications. Pool-based active learning m…
High Throughput Training of Deep Surrogates from Large Ensemble Runs
Lucas Meyer, Marc Schouler, Robert Alexander Caulk +2
Recent years have seen a surge in deep learning approaches to accelerate numerical solvers, which provide faithful but computationally intensive simulations of the physical world.…
Case Studies of Causal Discovery from IT Monitoring Time Series
Ali Aït-Bachir, Charles K. Assaad, Christophe de Bignicourt +5
Information technology (IT) systems are vital for modern businesses, handling data storage, communication, and process automation. Monitoring these systems is crucial for their pro…
Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space
Jonatha Anselmi, Bruno Gaujal, Louis-Sébastien Rebuffi
In this paper, we revisit the regret of undiscounted reinforcement learning in MDPs with a birth and death structure. Specifically, we consider a controlled queue with impatient jo…