Search Results for author: Ludovic Denoyer

Found 36 papers, 17 papers with code

SaLinA: Sequential Learning of Agents

1 code implementation15 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.

Learning a subspace of policies for online adaptation in Reinforcement Learning

1 code implementation11 Oct 2021 Jean-Baptiste Gaya, Laure Soulier, Ludovic Denoyer

There is a need to develop RL methods that generalize well to variations of the training conditions.

On Anytime Learning at Macroscale

no code implementations17 Jun 2021 Lucas Caccia, Jing Xu, Myle Ott, Marc'Aurelio Ranzato, Ludovic Denoyer

This creates a natural trade-off between accuracy of a model and time to obtain such a model.

Efficient Continual Learning with Modular Networks and Task-Driven Priors

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.

Continual Learning

Learning Dynamic Author Representations with Temporal Language Models

1 code implementation11 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.

Information Retrieval Language Modelling

Large Memory Layers with Product Keys

6 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.

Language Modelling

Binary Stochastic Representations for Large Multi-class Classification

no code implementations24 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.

Classification General Classification +1

Unsupervised Question Answering by Cloze Translation

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.

Question Answering Translation

EDUCE: Explaining model Decisions through Unsupervised Concepts Extraction

no code implementations28 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.

Sentiment Analysis Text Classification

Unsupervised Object Segmentation by Redrawing

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.

Semantic Segmentation Unsupervised Object Segmentation

Multiple-Attribute Text Rewriting

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".

Style Transfer Translation

Stochastic Adaptive Neural Architecture Search for Keyword Spotting

1 code implementation16 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.

Keyword Spotting Neural Architecture Search

Multiple-Attribute Text Style Transfer

2 code implementations1 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".

Style Transfer Text Style Transfer +1

Phrase-Based \& Neural Unsupervised Machine Translation

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.

Denoising Translation +1

Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery

no code implementations23 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.

Epidemiology Time Series +2

Phrase-Based & Neural Unsupervised Machine Translation

14 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.

Translation Unsupervised Machine Translation

Fader Networks:Manipulating Images by Sliding Attributes

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.

Multi-View Data Generation Without View Supervision

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.

Word Translation Without Parallel Data

16 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.

Translation Unsupervised Machine Translation +2

A Meta-Learning Approach to One-Step Active Learning

no code implementations26 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.

Active Learning Meta-Learning

Fader Networks: Manipulating Images by Sliding Attributes

3 code implementations1 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.

Learning Time/Memory-Efficient Deep Architectures with Budgeted Super Networks

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.

Options Discovery with Budgeted Reinforcement Learning

no code implementations21 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.

Multi-view Generative Adversarial Networks

no code implementations7 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.

Density Estimation General Classification

Sequential Cost-Sensitive Feature Acquisition

no code implementations13 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.

Representation Learning

Reinforced Decision Trees

no code implementations5 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.

Representation Learning for cold-start recommendation

no code implementations22 Dec 2014 Gabriella Contardo, Ludovic Denoyer, Thierry Artieres

Representations for both users and items are computed from the observed ratings and used for prediction.

Collaborative Filtering Representation Learning

Deep Sequential Neural Network

no code implementations2 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.

Learning States Representations in POMDP

no code implementations20 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.

Learning Information Spread in Content Networks

no code implementations20 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.

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