no code implementations • 28 Aug 2023 • Mingxi Tan, Andong Tian, Ludovic Denoyer
In this work, we propose a method called Moment-Matching Policy Diversity to alleviate this problem.
no code implementations • 18 Aug 2023 • Anthony Kobanda, Valliappan C. A., Joshua Romoff, Ludovic Denoyer
Deep reinforcement learning (DRL) techniques have become increasingly used in various fields for decision-making processes.
1 code implementation • 18 Nov 2022 • Jean-Baptiste Gaya, Thang Doan, Lucas Caccia, Laure Soulier, Ludovic Denoyer, Roberta Raileanu
We introduce Continual Subspace of Policies (CSP), a new approach that incrementally builds a subspace of policies for training a reinforcement learning agent on a sequence of tasks.
no code implementations • 27 Sep 2022 • Mingxi Tan, Andong Tian, Ludovic Denoyer
Existing imitation learning methods mainly focus on making an agent effectively mimic a demonstrated behavior, but do not address the potential contradiction between the behavior style and the objective of a task.
no code implementations • 31 May 2022 • Pierre Erbacher, Ludovic Denoyer, Laure Soulier
When users initiate search sessions, their queries are often unclear or might lack of context; this resulting in inefficient document ranking.
no code implementations • 21 Mar 2022 • Akram Erraqabi, Marlos C. Machado, Mingde Zhao, Sainbayar Sukhbaatar, Alessandro Lazaric, Ludovic Denoyer, Yoshua Bengio
In reinforcement learning, the graph Laplacian has proved to be a valuable tool in the task-agnostic setting, with applications ranging from skill discovery to reward shaping.
no code implementations • 11 Mar 2022 • Tyler L. Hayes, Maximilian Nickel, Christopher Kanan, Ludovic Denoyer, Arthur Szlam
Using this framing, we introduce an active sampling method that asks for examples from the tail of the data distribution and show that it outperforms classical active learning methods on Visual Genome.
no code implementations • 10 Jan 2022 • Pierre Erbacher, Laure Soulier, Ludovic Denoyer
Conversational Information Retrieval (CIR) is an emerging field of Information Retrieval (IR) at the intersection of interactive IR and dialogue systems for open domain information needs.
1 code implementation • ICML Workshop URL 2021 • Pierre-Alexandre Kamienny, Jean Tarbouriech, Sylvain Lamprier, Alessandro Lazaric, Ludovic Denoyer
Learning meaningful behaviors in the absence of reward is a difficult problem in reinforcement learning.
1 code implementation • 15 Oct 2021 • Ludovic Denoyer, Alfredo De la Fuente, Song Duong, Jean-Baptiste Gaya, Pierre-Alexandre Kamienny, Daniel H. Thompson
SaLinA is a simple library that makes implementing complex sequential learning models easy, including reinforcement learning algorithms.
1 code implementation • ICLR 2022 • Jean-Baptiste Gaya, Laure Soulier, Ludovic Denoyer
There is a need to develop RL methods that generalize well to variations of the training conditions.
1 code implementation • 17 Jun 2021 • Lucas Caccia, Jing Xu, Myle Ott, Marc'Aurelio Ranzato, Ludovic Denoyer
Practitioners have then to decide how to allocate their computational budget in order to obtain the best performance at any point in time.
no code implementations • ICML Workshop URL 2021 • Akram Erraqabi, Mingde Zhao, Marlos C. Machado, Yoshua Bengio, Sainbayar Sukhbaatar, Ludovic Denoyer, Alessandro Lazaric
In this work, we introduce a method that explicitly couples representation learning with exploration when the agent is not provided with a uniform prior over the state space.
no code implementations • 1 Jan 2021 • Pierre-Alexandre Kamienny, Matteo Pirotta, Alessandro Lazaric, Thibault Lavril, Nicolas Usunier, Ludovic Denoyer
Meta-reinforcement learning aims at finding a policy able to generalize to new environments.
2 code implementations • ICLR 2021 • Tom Veniat, Ludovic Denoyer, Marc'Aurelio Ranzato
Finally, we introduce a new modular architecture, whose modules represent atomic skills that can be composed to perform a certain task.
1 code implementation • 1 Jun 2020 • Federico Errica, Ludovic Denoyer, Bora Edizel, Fabio Petroni, Vassilis Plachouras, Fabrizio Silvestri, Sebastian Riedel
We propose a model to tackle classification tasks in the presence of very little training data.
1 code implementation • 6 May 2020 • Pierre-Alexandre Kamienny, Matteo Pirotta, Alessandro Lazaric, Thibault Lavril, Nicolas Usunier, Ludovic Denoyer
We test the performance of our algorithm in a variety of environments where tasks may vary within each episode.
no code implementations • 25 Sep 2019 • Federico Errica, Fabrizio Silvestri, Bora Edizel, Sebastian Riedel, Ludovic Denoyer, Vassilis Plachouras
We propose a model to tackle classification tasks in the presence of very little training data.
no code implementations • 25 Sep 2019 • Diane Bouchacourt, Ludovic Denoyer
Therefore, we propose a new self-interpretable model that performs output prediction and simultaneously provides an explanation in terms of the presence of particular concepts in the input.
1 code implementation • 11 Sep 2019 • Edouard Delasalles, Sylvain Lamprier, Ludovic Denoyer
By conditioning language models with author and temporal vector states, we are able to leverage the latent dependencies between the text contexts.
8 code implementations • NeurIPS 2019 • Guillaume Lample, Alexandre Sablayrolles, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou
In our experiments we consider a dataset with up to 30 billion words, and we plug our memory layer in a state-of-the-art transformer-based architecture.
no code implementations • 24 Jun 2019 • Thomas Gerald, Aurélia Léon, Nicolas Baskiotis, Ludovic Denoyer
Different models based on the notion of binary codes have been proposed to overcome this limitation, achieving in a sublinear inference complexity.
1 code implementation • ACL 2019 • Patrick Lewis, Ludovic Denoyer, Sebastian Riedel
We approach this problem by first learning to generate context, question and answer triples in an unsupervised manner, which we then use to synthesize Extractive QA training data automatically.
no code implementations • 28 May 2019 • Diane Bouchacourt, Ludovic Denoyer
Therefore, we propose a new self-interpretable model that performs output prediction and simultaneously provides an explanation in terms of the presence of particular concepts in the input.
1 code implementation • NeurIPS 2019 • Mickaël Chen, Thierry Artières, Ludovic Denoyer
Object segmentation is a crucial problem that is usually solved by using supervised learning approaches over very large datasets composed of both images and corresponding object masks.
no code implementations • ICLR 2019 • Guillaume Lample, Sandeep Subramanian, Eric Smith, Ludovic Denoyer, Marc'Aurelio Ranzato, Y-Lan Boureau
The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style".
1 code implementation • 16 Nov 2018 • Tom Véniat, Olivier Schwander, Ludovic Denoyer
The problem of keyword spotting i. e. identifying keywords in a real-time audio stream is mainly solved by applying a neural network over successive sliding windows.
3 code implementations • 1 Nov 2018 • Sandeep Subramanian, Guillaume Lample, Eric Michael Smith, Ludovic Denoyer, Marc'Aurelio Ranzato, Y-Lan Boureau
The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style".
no code implementations • EMNLP 2018 • Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, Marc{'}Aurelio Ranzato
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of language pairs.
no code implementations • WS 2018 • Wafa Aissa, Laure Soulier, Ludovic Denoyer
Search-oriented conversational systems rely on information needs expressed in natural language (NL).
no code implementations • 23 Apr 2018 • Ali Ziat, Edouard Delasalles, Ludovic Denoyer, Patrick Gallinari
We introduce a dynamical spatio-temporal model formalized as a recurrent neural network for forecasting time series of spatial processes, i. e. series of observations sharing temporal and spatial dependencies.
15 code implementations • EMNLP 2018 • Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, Marc'Aurelio Ranzato
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of language pairs.
Ranked #2 on Machine Translation on WMT2016 English-Russian
no code implementations • NeurIPS 2017 • Guillaume Lample, Neil Zeghidour, Nicolas Usunier, Antoine Bordes, Ludovic Denoyer, Marc'Aurelio Ranzato
This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space.
1 code implementation • ICLR 2018 • Mickaël Chen, Ludovic Denoyer, Thierry Artières
We assume that the distribution of the data is driven by two independent latent factors: the content, which represents the intrinsic features of an object, and the view, which stands for the settings of a particular observation of that object.
15 code implementations • ICLR 2018 • Guillaume Lample, Alexis Conneau, Ludovic Denoyer, Marc'Aurelio Ranzato
By learning to reconstruct in both languages from this shared feature space, the model effectively learns to translate without using any labeled data.
Ranked #7 on Machine Translation on WMT2016 German-English
19 code implementations • ICLR 2018 • Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer, Hervé Jégou
We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine translation.
Ranked #2 on Word Alignment on en-es
no code implementations • 26 Jun 2017 • Gabriella Contardo, Ludovic Denoyer, Thierry Artieres
More specifically, we consider a pool-based setting, where the system observes all the examples of the dataset of a problem and has to choose the subset of examples to label in a single shot.
3 code implementations • 1 Jun 2017 • Guillaume Lample, Neil Zeghidour, Nicolas Usunier, Antoine Bordes, Ludovic Denoyer, Marc'Aurelio Ranzato
This paper introduces a new encoder-decoder architecture that is trained to reconstruct images by disentangling the salient information of the image and the values of attributes directly in the latent space.
1 code implementation • CVPR 2018 • Tom Veniat, Ludovic Denoyer
We propose to focus on the problem of discovering neural network architectures efficient in terms of both prediction quality and cost.
no code implementations • 21 Nov 2016 • Aurélia Léon, Ludovic Denoyer
We consider the problem of learning hierarchical policies for Reinforcement Learning able to discover options, an option corresponding to a sub-policy over a set of primitive actions.
no code implementations • 7 Nov 2016 • Mickaël Chen, Ludovic Denoyer
Most related studies focus on the classification point of view and assume that all the views are available at any time.
no code implementations • 13 Jul 2016 • Gabriella Contardo, Ludovic Denoyer, Thierry Artières
We propose a reinforcement learning based approach to tackle the cost-sensitive learning problem where each input feature has a specific cost.
no code implementations • 5 May 2015 • Aurélia Léon, Ludovic Denoyer
In order to speed-up classification models when facing a large number of categories, one usual approach consists in organizing the categories in a particular structure, this structure being then used as a way to speed-up the prediction computation.
no code implementations • 22 Dec 2014 • Gabriella Contardo, Ludovic Denoyer, Thierry Artieres
Representations for both users and items are computed from the observed ratings and used for prediction.
no code implementations • 2 Oct 2014 • Ludovic Denoyer, Patrick Gallinari
Instead of considering global transformations, like in classical multilayer networks, this model allows us for learning a set of local transformations.
no code implementations • 20 Dec 2013 • Cédric Lagnier, Simon Bourigault, Sylvain Lamprier, Ludovic Denoyer, Patrick Gallinari
We introduce a model for predicting the diffusion of content information on social media.
no code implementations • 20 Dec 2013 • Gabriel Dulac-Arnold, Ludovic Denoyer, Nicolas Thome, Matthieu Cord, Patrick Gallinari
In this paper, we investigate a new framework for image classification that adaptively generates spatial representations.
no code implementations • 20 Dec 2013 • Gabriella Contardo, Ludovic Denoyer, Thierry Artieres, Patrick Gallinari
We propose to deal with sequential processes where only partial observations are available by learning a latent representation space on which policies may be accurately learned.