6 citations
- Institut de Recherche en Informatique de ToulouseFR4 papers
- Technology Solutions Experts (United States)US3 papers
- Institut Polytechnique de BordeauxFR2 papers
- Université Toulouse-I-CapitoleFR2 papers
- Université Toulouse III - Paul SabatierFR2 papers
- Université Toulouse - Jean JaurèsFR2 papers
- University of ToledoUS2 papers
- Centre National de la Recherche ScientifiqueFR1 paper
- Discovery Air (Canada)CA1 paper
- Institut national de recherche en sciences et technologies du numériqueFR1 paper
- Institut National des Sciences Appliquées de ToulouseFR1 paper
- International Commission on IlluminationAT1 paper
10 papers
Bilevel gradient methods and the Morse parametric qualification condition
Jérôme Bolte, Quoc-Tung Le, Edouard Pauwels +1
We introduce the Morse parametric qualification condition for bilevel programming. Generic semi-algebraic functions are Morse parametric in a piecewise sense. Thus, bilevel program…
A second-order-like optimizer with adaptive gradient scaling for deep learning
Jérôme Bolte, Ryan Boustany, Edouard Pauwels +1
In this empirical article, we introduce INNAprop, an optimization algorithm that combines the INNA method with the RMSprop adaptive gradient scaling. It leverages second-order info…
Geometric and computational hardness of bilevel programming
Jérôme Bolte, Quoc-Tung Le, Edouard Pauwels +1
We first show a simple but striking result in bilevel optimization: unconstrained smooth bilevel programming is as hard as general extended-real-valued lower semicontinu…
Improved Performances and Motivation in Intelligent Tutoring Systems: Combining Machine Learning and Learner Choice
Benjamin Clément, Hélène Sauzéon, Didier Roy +1
Large class sizes challenge personalized learning in schools, prompting the use of educational technologies such as intelligent tutoring systems. To address this, we present an AI-…
The complexity of unsupervised learning of lexicographic preferences
Hélène Fargier, Pierre-François Gimenez, Jérôme Mengin +1
This paper considers the task of learning users' preferences on a combinatorial set of alternatives, as generally used by online configurators, for example. In many settings, only…
A measure for characterizing heavy-tailed networks
Scott A. Hill
Heavy-tailed networks are often characterized in the literature by their degree distribution's similarity to a power law. However, many heavy-tailed networks in real life do not ha…