146 citations
- Université Paris Dauphine-PSLFR65 papers
- Centre National de la Recherche ScientifiqueFR52 papers
- Université Paris Sciences et LettresFR27 papers
- University of LuxembourgLU9 papers
- École Nationale de l’Aviation CivileFR6 papers
- Institut Universitaire de FranceFR6 papers
- Laboratoire d'Intégration des Systèmes et des TechnologiesFR5 papers
- AGH University of KrakowPL4 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR4 papers
- Hungarian Academy of SciencesHU4 papers
- Korea Advanced Institute of Science and TechnologyKR4 papers
- Laboratoire des Sciences pour la Conception, l'Optimisation et la ProductionFR4 papers
8 papers · 1 filter
First Order Logic on Pathwidth Revisited Again
Michael Lampis
Courcelle's celebrated theorem states that all MSO-expressible properties can be decided in linear time on graphs of bounded treewidth. Unfortunately, the hidden constant implied b…
Lower bound for constant-size local certification
Virgina Ardévol Martínez, Marco Caoduro, Laurent Feuilloley +3
Given a network property or a data structure, a local certification is a labeling that allows to efficiently check that the property is satisfied, or that the structure is correct.…
Smooth Fictitious Play in Stochastic Games with Perturbed Payoffs and Unknown Transitions
Lucas Baudin, Rida Laraki
Recent extensions to dynamic games of the well-known fictitious play learning procedure in static games were proved to globally converge to stationary Nash equilibria in two import…
Is the U-Net Directional-Relationship Aware?
Mateus Riva, Pietro Gori, Florian Yger +1
CNNs are often assumed to be capable of using contextual information about distinct objects (such as their directional relations) inside their receptive field. However, the nature…
Cautious Learning of Multiattribute Preferences
Hugo Gilbert, Mohamed Ouaguenouni, Meltem Ozturk +1
This paper is dedicated to a cautious learning methodology for predicting preferences between alternatives characterized by binary attributes (formally, each alternative is seen as…
Towards Consistency in Adversarial Classification
Laurent Meunier, Raphaël Ettedgui, Rafael Pinot +2
In this paper, we study the problem of consistency in the context of adversarial examples. Specifically, we tackle the following question: can surrogate losses still be used as a p…