Search Results for author: Sylvain Le Corff

Found 21 papers, 8 papers with code

End-to-end deep meta modelling to calibrate and optimize energy consumption and comfort

1 code implementation1 Feb 2021 Max Cohen, Sylvain Le Corff, Maurice Charbit, Marius Preda, Gilles Nozière

Parameters are estimated by comparing the predictions of the metamodel with real data obtained from sensors using the CMA-ES algorithm, a derivative free optimization procedure.

Multiobjective Optimization

Joint self-supervised blind denoising and noise estimation

1 code implementation16 Feb 2021 Jean Ollion, Charles Ollion, Elisabeth Gassiat, Luc Lehéricy, Sylvain Le Corff

Assuming that the noisy observations are independent conditionally to the signal, the networks can be jointly trained without clean training data.

Image Denoising Noise Estimation

Diffusion bridges vector quantized Variational AutoEncoders

1 code implementation10 Feb 2022 Max Cohen, Guillaume Quispe, Sylvain Le Corff, Charles Ollion, Eric Moulines

In this work, we propose a new model to train the prior and the encoder/decoder networks simultaneously.

Learning Natural Language Generation with Truncated Reinforcement Learning

1 code implementation NAACL 2022 Alice Martin, Guillaume Quispe, Charles Ollion, Sylvain Le Corff, Florian Strub, Olivier Pietquin

To our knowledge, it is the first approach that successfully learns a language generation policy without pre-training, using only reinforcement learning.

Language Modelling Question Generation +4

End-to-end deep metamodeling to calibrate and optimize energy loads

no code implementations19 Jun 2020 Max Cohen, Maurice Charbit, Sylvain Le Corff, Marius Preda, Gilles Nozière

Finally, the optimal settings to minimize the energy loads while maintaining a target thermal comfort and air quality are obtained using a multi-objective optimization procedure.

Management

The Monte Carlo Transformer: a stochastic self-attention model for sequence prediction

no code implementations15 Jul 2020 Alice Martin, Charles Ollion, Florian Strub, Sylvain Le Corff, Olivier Pietquin

This paper introduces the Sequential Monte Carlo Transformer, an original approach that naturally captures the observations distribution in a transformer architecture.

NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform

1 code implementation17 Mar 2021 Achille Thin, Yazid Janati, Sylvain Le Corff, Charles Ollion, Arnaud Doucet, Alain Durmus, Eric Moulines, Christian Robert

Sampling from a complex distribution $\pi$ and approximating its intractable normalizing constant Z are challenging problems.

Learning Natural Language Generation from Scratch

no code implementations20 Sep 2021 Alice Martin Donati, Guillaume Quispe, Charles Ollion, Sylvain Le Corff, Florian Strub, Olivier Pietquin

This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original ap-proach to train conditional language models from scratch by only using reinforcement learning (RL).

Language Modelling reinforcement-learning +2

NEO: Non Equilibrium Sampling on the Orbits of a Deterministic Transform

1 code implementation NeurIPS 2021 Achille Thin, Yazid Janati El Idrissi, Sylvain Le Corff, Charles Ollion, Eric Moulines, Arnaud Doucet, Alain Durmus, Christian Robert

Sampling from a complex distribution $\pi$ and approximating its intractable normalizing constant $\mathrm{Z}$ are challenging problems.

State and parameter learning with PaRIS particle Gibbs

no code implementations2 Jan 2023 Gabriel Cardoso, Yazid Janati El Idrissi, Sylvain Le Corff, Eric Moulines, Jimmy Olsson

The particle-based, rapid incremental smoother PaRIS is a sequential Monte Carlo (SMC) technique allowing for efficient online approximation of expectations of additive functionals under the smoothing distribution in these models.

Asymptotic convergence of iterative optimization algorithms

no code implementations24 Feb 2023 Randal Douc, Sylvain Le Corff

This paper introduces a general framework for iterative optimization algorithms and establishes under general assumptions that their convergence is asymptotically geometric.

Variational latent discrete representation for time series modelling

no code implementations27 Jun 2023 Max Cohen, Maurice Charbit, Sylvain Le Corff

Discrete latent space models have recently achieved performance on par with their continuous counterparts in deep variational inference.

Management Time Series +1

Monte Carlo guided Diffusion for Bayesian linear inverse problems

no code implementations15 Aug 2023 Gabriel Cardoso, Yazid Janati El Idrissi, Sylvain Le Corff, Eric Moulines

Ill-posed linear inverse problems arise frequently in various applications, from computational photography to medical imaging.

Bayesian Inference

Variational excess risk bound for general state space models

no code implementations15 Dec 2023 Élisabeth Gassiat, Sylvain Le Corff

In this paper, we consider variational autoencoders (VAE) for general state space models.

Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation

no code implementations5 Feb 2024 Sobihan Surendran, Antoine Godichon-Baggioni, Adeline Fermanian, Sylvain Le Corff

This paper provides a comprehensive non-asymptotic analysis of SGD with biased gradients and adaptive steps for convex and non-convex smooth functions.

Importance sampling for online variational learning

no code implementations5 Feb 2024 Mathis Chagneux, Pierre Gloaguen, Sylvain Le Corff, Jimmy Olsson

This article addresses online variational estimation in state-space models.

An analysis of the noise schedule for score-based generative models

no code implementations7 Feb 2024 Stanislas Strasman, Antonio Ocello, Claire Boyer, Sylvain Le Corff, Vincent Lemaire

Under mild assumptions on the data distribution, we establish an upper bound for the KL divergence between the target and the estimated distributions, explicitly depending on any time-dependent noise schedule.

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