Search Results for author: Olivier Teytaud

Found 29 papers, 5 papers with code

PrivacyGAN: robust generative image privacy

no code implementations19 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.

Data Poisoning Image Generation

Fairness in generative modeling

no code implementations6 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.


Improving Nevergrad's Algorithm Selection Wizard NGOpt through Automated Algorithm Configuration

no code implementations9 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.

CompilerGym: Robust, Performant Compiler Optimization Environments for AI Research

1 code implementation17 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.

Compiler Optimization OpenAI Gym

Asymptotic convergence rates for averaging strategies

no code implementations10 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.

Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants

no code implementations24 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.

Board Games Transfer Learning

Deep Learning for General Game Playing with Ludii and Polygames

1 code implementation23 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.

Board Games

Black-Box Optimization Revisited: Improving Algorithm Selection Wizards through Massive Benchmarking

no code implementations8 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.


EvolGAN: Evolutionary Generative Adversarial Networks

1 code implementation28 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.

Population Control meets Doob's Martingale Theorems: the Noise-free Multimodal Case

no code implementations24 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.

Versatile Black-Box Optimization

no code implementations29 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.

Combinatorial Optimization Evolutionary Algorithms

On averaging the best samples in evolutionary computation

no code implementations24 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 $\mu=1$.

Variance Reduction for Better Sampling in Continuous Domains

no code implementations24 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.

Yet another but more efficient black-box adversarial attack: tiling and evolution strategies

no code implementations5 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.

Adversarial Attack

Inspirational Adversarial Image Generation

1 code implementation17 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.

Image Generation

Exact Distributed Training: Random Forest with Billions of Examples

no code implementations18 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.

PSO-based Fuzzy Markup Language for Student Learning Performance Evaluation and Educational Application

no code implementations24 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.

Toward Optimal Run Racing: Application to Deep Learning Calibration

no code implementations10 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.

One-Shot Learning Two-sample testing

Automatically Reinforcing a Game AI

no code implementations27 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.

Exploration vs Exploitation vs Safety: Risk-averse Multi-Armed Bandits

no code implementations6 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.

energy management Management +1

Cannot find the paper you are looking for? You can Submit a new open access paper.