1.7k citations
- Centre National de la Recherche ScientifiqueFR209 papers
- Université Grenoble AlpesFR163 papers
- Institut polytechnique de GrenobleFR140 papers
- Grain Inspection, Packers and Stockyards AdministrationUS56 papers
- Laboratoire d'Informatique de GrenobleFR38 papers
- Centre Inria de l'Université Grenoble AlpesFR37 papers
- Institut national de recherche en sciences et technologies du numériqueFR33 papers
- Laboratoire des signaux et systèmesFR22 papers
- CentraleSupélecFR17 papers
- Sorbonne UniversitéFR16 papers
- Laboratoire Jean KuntzmannFR15 papers
- Centre de Recherche en Informatique, Signal et Automatique de LilleFR14 papers
27 papers · 1 filter
Mechanistic Interpretability as Statistical Estimation: A Variance Analysis
Maxime Méloux, François Portet, Maxime Peyrard
Mechanistic Interpretability (MI) aims to reverse-engineer model behaviors by identifying functional sub-networks. Yet, the scientific validity of these findings depends on their s…
Augmented Invertible Koopman Autoencoder for long-term time series forecasting
Anthony Frion, Lucas Drumetz, Mauro Dalla Mura +2
Following the introduction of Dynamic Mode Decomposition and its numerous extensions, many neural autoencoder-based implementations of the Koopman operator have recently been propo…
Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?
Maxime Méloux, Silviu Maniu, François Portet +1
As AI systems are used in high-stakes applications, ensuring interpretability is crucial. Mechanistic Interpretability (MI) aims to reverse-engineer neural networks by extracting h…
Meta-Statistical Learning: Supervised Learning of Statistical Estimators
Maxime Peyrard, Kyunghyun Cho
Statistical inference, a central tool of science, revolves around the study and the usage of statistical estimators: functions that map finite samples to predictions about unknown…
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…
Enhancing Reinforcement Learning Agents with Local Guides
Paul Daoudi, Bogdan Robu, Christophe Prieur +2
This paper addresses the problem of integrating local guide policies into a Reinforcement Learning agent. For this, we show how to adapt existing algorithms to this setting before…