no code implementations • 19 Oct 2023 • Mariia Zameshina, Olivier Teytaud, Laurent Najman
Latent diffusion models excel at producing high-quality images from text.
no code implementations • 19 Oct 2023 • Mariia Zameshina, Marlene Careil, Olivier Teytaud, Laurent Najman
Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images resembling the original only in several characteristics, such as gender, ethnicity, or facial expression. In this study, we introduce a novel approach, PrivacyGAN, that uses the power of image generation techniques, such as VQGAN and StyleGAN, to safeguard privacy while maintaining image usability, particularly for social media applications.
no code implementations • 29 Sep 2023 • Elena Raponi, Nathanael Rakotonirina Carraz, Jérémy Rapin, Carola Doerr, Olivier Teytaud
BO-based algorithms are popular in the ML community, as they are used for hyperparameter optimization and more generally for algorithm configuration.
no code implementations • 6 Oct 2022 • Mariia Zameshina, Olivier Teytaud, Fabien Teytaud, Vlad Hosu, Nathanael Carraz, Laurent Najman, Markus Wagner
We design general-purpose algorithms for addressing fairness issues and mode collapse in generative modeling.
no code implementations • 9 Sep 2022 • Risto Trajanov, Ana Nikolikj, Gjorgjina Cenikj, Fabien Teytaud, Mathurin Videau, Olivier Teytaud, Tome Eftimov, Manuel López-Ibáñez, Carola Doerr
Algorithm selection wizards are effective and versatile tools that automatically select an optimization algorithm given high-level information about the problem and available computational resources, such as number and type of decision variables, maximal number of evaluations, possibility to parallelize evaluations, etc.
no code implementations • 29 Sep 2021 • Elena Raponi, Nathanaël Carraz Rakotonirina, Jérémy Rapin, Olivier Teytaud, Carola Doerr
Machine learning has invaded various domains of computer science, including black-box optimization.
1 code implementation • 17 Sep 2021 • Chris Cummins, Bram Wasti, Jiadong Guo, Brandon Cui, Jason Ansel, Sahir Gomez, Somya Jain, Jia Liu, Olivier Teytaud, Benoit Steiner, Yuandong Tian, Hugh Leather
What is needed is an easy, reusable experimental infrastructure for real world compiler optimization tasks that can serve as a common benchmark for comparing techniques, and as a platform to accelerate progress in the field.
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 • 24 Feb 2021 • Dennis J. N. J. Soemers, Vegard Mella, Eric Piette, Matthew Stephenson, Cameron Browne, Olivier Teytaud
In this paper, we use fully convolutional architectures in AlphaZero-like self-play training setups to facilitate transfer between variants of board games as well as distinct games.
1 code implementation • 23 Jan 2021 • Dennis J. N. J. Soemers, Vegard Mella, Cameron Browne, Olivier Teytaud
Combinations of Monte-Carlo tree search and Deep Neural Networks, trained through self-play, have produced state-of-the-art results for automated game-playing in many board games.
no code implementations • 8 Oct 2020 • Laurent Meunier, Herilalaina Rakotoarison, Pak Kan Wong, Baptiste Roziere, Jeremy Rapin, Olivier Teytaud, Antoine Moreau, Carola Doerr
We demonstrate the advantages of such a broad collection by deriving from it Automated Black Box Optimizer (ABBO), a general-purpose algorithm selection wizard.
1 code implementation • 28 Sep 2020 • Baptiste Roziere, Fabien Teytaud, Vlad Hosu, Hanhe Lin, Jeremy Rapin, Mariia Zameshina, Olivier Teytaud
We propose to use a quality estimator and evolutionary methods to search the latent space of generative adversarial networks trained on small, difficult datasets, or both.
1 code implementation • 25 Sep 2020 • Baptiste Roziere, Nathanal Carraz Rakotonirina, Vlad Hosu, Andry Rasoanaivo, Hanhe Lin, Camille Couprie, Olivier Teytaud
More generally, our approach can be used to optimize any method based on noise injection.
no code implementations • 24 May 2020 • Marie-Liesse Cauwet, Olivier Teytaud
We study a test-based population size adaptation (TBPSA) method, inspired from population control, in the noise-free multimodal case.
no code implementations • 29 Apr 2020 • Jialin Liu, Antoine Moreau, Mike Preuss, Baptiste Roziere, Jeremy Rapin, Fabien Teytaud, Olivier Teytaud
Choosing automatically the right algorithm using problem descriptors is a classical component of combinatorial optimization.
no code implementations • 24 Apr 2020 • Laurent Meunier, Carola Doerr, Jeremy Rapin, Olivier Teytaud
Design of experiments, random search, initialization of population-based methods, or sampling inside an epoch of an evolutionary algorithm use a sample drawn according to some probability distribution for approximating the location of an optimum.
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 $\mu=1$.
no code implementations • NeurIPS 2020 • Evrard Garcelon, Baptiste Roziere, Laurent Meunier, Jean Tarbouriech, Olivier Teytaud, Alessandro Lazaric, Matteo Pirotta
In many of these domains, malicious agents may have incentives to attack the bandit algorithm to induce it to perform a desired behavior.
no code implementations • 27 Jan 2020 • Tristan Cazenave, Yen-Chi Chen, Guan-Wei Chen, Shi-Yu Chen, Xian-Dong Chiu, Julien Dehos, Maria Elsa, Qucheng Gong, Hengyuan Hu, Vasil Khalidov, Cheng-Ling Li, Hsin-I Lin, Yu-Jin Lin, Xavier Martinet, Vegard Mella, Jeremy Rapin, Baptiste Roziere, Gabriel Synnaeve, Fabien Teytaud, Olivier Teytaud, Shi-Cheng Ye, Yi-Jun Ye, Shi-Jim Yen, Sergey Zagoruyko
Since DeepMind's AlphaZero, Zero learning quickly became the state-of-the-art method for many board games.
no code implementations • 5 Oct 2019 • Laurent Meunier, Jamal Atif, Olivier Teytaud
In the targeted setting, we are able to reach, with a limited budget of $100, 000$, $100\%$ of success rate with a budget of $6, 662$ queries on average, i. e. we need $800$ queries less than the current state of the art.
1 code implementation • 17 Jun 2019 • Baptiste Rozière, Morgane Riviere, Olivier Teytaud, Jérémy Rapin, Yann Lecun, Camille Couprie
We design a simple optimization method to find the optimal latent parameters corresponding to the closest generation to any input inspirational image.
no code implementations • 18 Apr 2018 • Mathieu Guillame-Bert, Olivier Teytaud
We introduce an exact distributed algorithm to train Random Forest models as well as other decision forest models without relying on approximating best split search.
no code implementations • 24 Feb 2018 • Chang-Shing Lee, Mei-Hui Wang, Chi-Shiang Wang, Olivier Teytaud, Jialin Liu, Su-Wei Lin, Pi-Hsia Hung
This paper proposes an agent with particle swarm optimization (PSO) based on a Fuzzy Markup Language (FML) for students learning performance evaluation and educational applications, and the proposed agent is according to the response data from a conventional test and an item response theory.
no code implementations • 10 Jun 2017 • Olivier Bousquet, Sylvain Gelly, Karol Kurach, Marc Schoenauer, Michele Sebag, Olivier Teytaud, Damien Vincent
This paper aims at one-shot learning of deep neural nets, where a highly parallel setting is considered to address the algorithm calibration problem - selecting the best neural architecture and learning hyper-parameter values depending on the dataset at hand.
no code implementations • 10 Jun 2017 • Olivier Bousquet, Sylvain Gelly, Karol Kurach, Olivier Teytaud, Damien Vincent
The selection of hyper-parameters is critical in Deep Learning.
no code implementations • 23 May 2017 • Karol Kurach, Sylvain Gelly, Michal Jastrzebski, Philip Haeusser, Olivier Teytaud, Damien Vincent, Olivier Bousquet
Generic text embeddings are successfully used in a variety of tasks.
no code implementations • 27 Jul 2016 • David L. St-Pierre, Jean-Baptiste Hoock, Jialin Liu, Fabien Teytaud, Olivier Teytaud
In addition, we consider the case in which only one GPP is available - by decomposing this single GPP into several ones through the use of parameters or even simply random seeds.
no code implementations • 8 Jul 2016 • Tristan Cazenave, Jialin Liu, Fabien Teytaud, Olivier Teytaud
Many artificial intelligences (AIs) are randomized.
no code implementations • 6 Jan 2014 • Nicolas Galichet, Michèle Sebag, Olivier Teytaud
Motivated by applications in energy management, this paper presents the Multi-Armed Risk-Aware Bandit (MARAB) algorithm.