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.

1 code implementation • 17 Apr 2024 • Etienne David, Jean Bellot, Sylvain Le Corff

The main challenge is to model a rich variety of time series, leverage any available external signals and provide sharp predictions with statistical guarantees.

1 code implementation • 11 Apr 2024 • Julia Linhart, Gabriel Victorino Cardoso, Alexandre Gramfort, Sylvain Le Corff, Pedro L. C. Rodrigues

Determining which parameters of a non-linear model could best describe a set of experimental data is a fundamental problem in science and it has gained much traction lately with the rise of complex large-scale simulators (a. k. a.

no code implementations • 7 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.

no code implementations • 5 Feb 2024 • Mathis Chagneux, Pierre Gloaguen, Sylvain Le Corff, Jimmy Olsson

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

no code implementations • 5 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.

no code implementations • 15 Dec 2023 • Élisabeth Gassiat, Sylvain Le Corff

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

1 code implementation • 15 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.

no code implementations • 4 Jul 2023 • Max Cohen, Maurice Charbit, Sylvain Le Corff

As sequential neural architectures become deeper and more complex, uncertainty estimation is more and more challenging.

no code implementations • 27 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.

no code implementations • 24 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.

no code implementations • 2 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.

no code implementations • 1 Jun 2022 • Mathis Chagneux, Élisabeth Gassiat, Pierre Gloaguen, Sylvain Le Corff

We consider the problem of state estimation in general state-space models using variational inference.

1 code implementation • 10 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.

2 code implementations • 7 Feb 2022 • Etienne David, Jean Bellot, Sylvain Le Corff

Secondly, to leverage such a dataset, we propose a new hybrid forecasting model.

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.

no code implementations • 20 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).

1 code implementation • NeurIPS 2021 • Hermanni Hälvä, Sylvain Le Corff, Luc Lehéricy, Jonathan So, Yongjie Zhu, Elisabeth Gassiat, Aapo Hyvarinen

We introduce a new general identifiable framework for principled disentanglement referred to as Structured Nonlinear Independent Component Analysis (SNICA).

1 code implementation • 17 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.

1 code implementation • 16 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.

1 code implementation • 1 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.

no code implementations • 15 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.

no code implementations • 19 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.

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

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.