no code implementations • ICML 2020 • Rafael Pinot, Raphael Ettedgui, Geovani Rizk, Yann Chevaleyre, Jamal Atif
We demonstrate the non-existence of a Nash equilibrium in our game when the classifier and the adversary are both deterministic, hence giving a negative answer to the above question in the deterministic regime.
no code implementations • 16 Feb 2024 • Florian Le Bronnec, Alexandre Verine, Benjamin Negrevergne, Yann Chevaleyre, Alexandre Allauzen
This paper introduces a novel evaluation framework for Large Language Models (LLMs) such as Llama-2 and Mistral, focusing on the adaptation of Precision and Recall metrics from image generation to text generation.
no code implementations • 1 Nov 2023 • Alexandre Verine, Muni Sreenivas Pydi, Benjamin Negrevergne, Yann Chevaleyre
Rejection sampling methods have recently been proposed to improve the performance of discriminator-based generative models.
Ranked #14 on Image Generation on CelebA 64x64
no code implementations • 20 Jul 2023 • Lucas Gnecco Heredia, Benjamin Negrevergne, Yann Chevaleyre
However, it has been shown that existing attacks are not well suited for this kind of classifiers.
no code implementations • 1 Feb 2023 • Alexandre Verine, Benjamin Negrevergne, Muni Sreenivas Pydi, Yann Chevaleyre
Generative models can have distinct mode of failures like mode dropping and low quality samples, which cannot be captured by a single scalar metric.
no code implementations • 3 Jun 2022 • Raphael Ettedgui, Alexandre Araujo, Rafael Pinot, Yann Chevaleyre, Jamal Atif
We first show that these certificates use too little information about the classifier, and are in particular blind to the local curvature of the decision boundary.
no code implementations • 1 Jun 2022 • Geovani Rizk, Igor Colin, Albert Thomas, Rida Laraki, Yann Chevaleyre
We propose the first regret-based approach to the Graphical Bilinear Bandits problem, where $n$ agents in a graph play a stochastic bilinear bandit game with each of their neighbors.
no code implementations • 20 May 2022 • Laurent Meunier, Raphaël Ettedgui, Rafael Pinot, Yann Chevaleyre, Jamal Atif
In this paper, we expose some pathological behaviors specific to the adversarial problem, and show that no convex surrogate loss can be consistent or calibrated in this context.
no code implementations • 10 Aug 2021 • Laurent Meunier, Iskander Legheraba, Yann Chevaleyre, Olivier Teytaud
Averaging the $\mu$ best individuals among the $\lambda$ evaluations is known to provide better estimates of the optimum of a function than just picking up the best.
no code implementations • ICML Workshop INNF 2021 • Alexandre Verine, Benjamin Negrevergne, Fabrice Rossi, Yann Chevaleyre
An invertible function is bi-Lipschitz if both the function and its inverse have bounded Lipschitz constants.
no code implementations • 22 Feb 2021 • Rafael Pinot, Laurent Meunier, Florian Yger, Cédric Gouy-Pailler, Yann Chevaleyre, Jamal Atif
This paper investigates the theory of robustness against adversarial attacks.
no code implementations • 13 Feb 2021 • Laurent Meunier, Meyer Scetbon, Rafael Pinot, Jamal Atif, Yann Chevaleyre
This paper tackles the problem of adversarial examples from a game theoretic point of view.
no code implementations • 14 Dec 2020 • Geovani Rizk, Albert Thomas, Igor Colin, Rida Laraki, Yann Chevaleyre
We study the best arm identification problem in which the learner wants to find the graph allocation maximizing the sum of the bilinear rewards.
2 code implementations • 15 Jun 2020 • Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif
This paper tackles the problem of Lipschitz regularization of Convolutional Neural Networks.
no code implementations • 24 Apr 2020 • Laurent Meunier, Yann Chevaleyre, Jeremy Rapin, Clément W. Royer, Olivier Teytaud
With our choice of selection rate, we get a provable regret of order $O(\lambda^{-1})$ which has to be compared with $O(\lambda^{-2/d})$ in the case where $\mu=1$.
1 code implementation • 26 Feb 2020 • Rafael Pinot, Raphael Ettedgui, Geovani Rizk, Yann Chevaleyre, Jamal Atif
We demonstrate the non-existence of a Nash equilibrium in our game when the classifier and the Adversary are both deterministic, hence giving a negative answer to the above question in the deterministic regime.
no code implementations • 1 Oct 2019 • Alexis Duburcq, Yann Chevaleyre, Nicolas Bredeche, Guilhem Boéris
Autonomous robots require online trajectory planning capability to operate in the real world.
no code implementations • ICLR 2019 • Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif
Recent results from linear algebra stating that any matrix can be decomposed into products of diagonal and circulant matrices has lead to the design of compact deep neural network architectures that perform well in practice.
no code implementations • 29 Jan 2019 • Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif
In this paper, we study deep diagonal circulant neural networks, that is deep neural networks in which weight matrices are the product of diagonal and circulant ones.
1 code implementation • 2 Oct 2018 • Alexandre Araujo, Benjamin Negrevergne, Yann Chevaleyre, Jamal Atif
In real world scenarios, model accuracy is hardly the only factor to consider.
no code implementations • 23 Jun 2018 • Thanh Hai Nguyen, Edi Prifti, Yann Chevaleyre, Nataliya Sokolovska, Jean-Daniel Zucker
Generally, when the sample size ($N$) is much bigger than the number of features ($d$), DL often outperforms other machine learning (ML) techniques, often through the use of Convolutional Neural Networks (CNNs).
no code implementations • 1 Dec 2017 • Thanh Hai Nguyen, Yann Chevaleyre, Edi Prifti, Nataliya Sokolovska, Jean-Daniel Zucker
However, in many bioinformatics ML tasks, we encounter the opposite situation where d is greater than N. In these situations, applying DL techniques (such as feed-forward networks) would lead to severe overfitting.