Search Results for author: Nicolas Usunier

Found 54 papers, 25 papers with code

Code Llama: Open Foundation Models for Code

2 code implementations24 Aug 2023 Baptiste Rozière, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Romain Sauvestre, Tal Remez, Jérémy Rapin, Artyom Kozhevnikov, Ivan Evtimov, Joanna Bitton, Manish Bhatt, Cristian Canton Ferrer, Aaron Grattafiori, Wenhan Xiong, Alexandre Défossez, Jade Copet, Faisal Azhar, Hugo Touvron, Louis Martin, Nicolas Usunier, Thomas Scialom, Gabriel Synnaeve

We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks.

Code Generation Instruction Following

Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers

no code implementations16 Feb 2023 Melissa Hall, Bobbie Chern, Laura Gustafson, Denisse Ventura, Harshad Kulkarni, Candace Ross, Nicolas Usunier

These metrics successfully incentivized performance improvements on person-centric tasks such as face analysis and are used to understand risks of modern models.

Fairness Multi-Label Image Classification +1

Leveraging Demonstrations with Latent Space Priors

1 code implementation26 Oct 2022 Jonas Gehring, Deepak Gopinath, Jungdam Won, Andreas Krause, Gabriel Synnaeve, Nicolas Usunier

Starting with a learned joint latent space, we separately train a generative model of demonstration sequences and an accompanying low-level policy.

Offline RL

Contextual bandits with concave rewards, and an application to fair ranking

no code implementations18 Oct 2022 Virginie Do, Elvis Dohmatob, Matteo Pirotta, Alessandro Lazaric, Nicolas Usunier

We consider Contextual Bandits with Concave Rewards (CBCR), a multi-objective bandit problem where the desired trade-off between the rewards is defined by a known concave objective function, and the reward vector depends on an observed stochastic context.

Fairness Multi-Armed Bandits

Fast online ranking with fairness of exposure

no code implementations13 Sep 2022 Nicolas Usunier, Virginie Do, Elvis Dohmatob

In this paper, we propose the first efficient online algorithm to optimize concave objective functions in the space of rankings which applies to every concave and smooth objective function, such as the ones found for fairness of exposure.

Fairness Recommendation Systems

Measuring and signing fairness as performance under multiple stakeholder distributions

no code implementations20 Jul 2022 David Lopez-Paz, Diane Bouchacourt, Levent Sagun, Nicolas Usunier

By highlighting connections to the literature in domain generalization, we propose to measure fairness as the ability of the system to generalize under multiple stress tests -- distributions of examples with social relevance.

Domain Generalization Fairness

Optimizing generalized Gini indices for fairness in rankings

no code implementations2 Apr 2022 Virginie Do, Nicolas Usunier

Depending on these weights, GGFs minimize the Gini index of item exposure to promote equality between items, or focus on the performance on specific quantiles of least satisfied users.

Fairness Recommendation Systems

Fairness Indicators for Systematic Assessments of Visual Feature Extractors

1 code implementation15 Feb 2022 Priya Goyal, Adriana Romero Soriano, Caner Hazirbas, Levent Sagun, Nicolas Usunier

Systematic diagnosis of fairness, harms, and biases of computer vision systems is an important step towards building socially responsible systems.

Fairness

Hierarchical Skills for Efficient Exploration

1 code implementation NeurIPS 2021 Jonas Gehring, Gabriel Synnaeve, Andreas Krause, Nicolas Usunier

We alleviate the need for prior knowledge by proposing a hierarchical skill learning framework that acquires skills of varying complexity in an unsupervised manner.

Continuous Control Efficient Exploration +4

Online Selection of Diverse Committees

no code implementations19 May 2021 Virginie Do, Jamal Atif, Jérôme Lang, Nicolas Usunier

Citizens' assemblies need to represent subpopulations according to their proportions in the general population.

Online certification of preference-based fairness for personalized recommender systems

no code implementations29 Apr 2021 Virginie Do, Sam Corbett-Davies, Jamal Atif, Nicolas Usunier

We propose to audit for envy-freeness, a more granular criterion aligned with individual preferences: every user should prefer their recommendations to those of other users.

Fairness Multi-Armed Bandits +1

Gradient Matching for Domain Generalization

2 code implementations ICLR 2022 Yuge Shi, Jeffrey Seely, Philip H. S. Torr, N. Siddharth, Awni Hannun, Nicolas Usunier, Gabriel Synnaeve

We perform experiments on both the Wilds benchmark, which captures distribution shift in the real world, as well as datasets in DomainBed benchmark that focuses more on synthetic-to-real transfer.

Domain Generalization

A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings

no code implementations17 Apr 2021 Eltayeb Ahmed, Luisa Zintgraf, Christian A. Schroeder de Witt, Nicolas Usunier

In this work we explore an auxiliary loss useful for reinforcement learning in environments where strong performing agents are required to be able to navigate a spatial environment.

Navigate

On ranking via sorting by estimated expected utility

no code implementations NeurIPS 2020 Clement Calauzenes, Nicolas Usunier

We provide an answer to this question in the form of a structural characterization of ranking losses for which a suitable regression is consistent.

regression

Tensor Decompositions for temporal knowledge base completion

2 code implementations ICLR 2020 Timothée Lacroix, Guillaume Obozinski, Nicolas Usunier

Additionally, we propose a new dataset for knowledge base completion constructed from Wikidata, larger than previous benchmarks by an order of magnitude, as a new reference for evaluating temporal and non-temporal link prediction methods.

Knowledge Base Completion Link Prediction +3

A Simple Convergence Proof of Adam and Adagrad

no code implementations5 Mar 2020 Alexandre Défossez, Léon Bottou, Francis Bach, Nicolas Usunier

We provide a simple proof of convergence covering both the Adam and Adagrad adaptive optimization algorithms when applied to smooth (possibly non-convex) objective functions with bounded gradients.

Music Source Separation in the Waveform Domain

1 code implementation27 Nov 2019 Alexandre Défossez, Nicolas Usunier, Léon Bottou, Francis Bach

Source separation for music is the task of isolating contributions, or stems, from different instruments recorded individually and arranged together to form a song.

Audio Generation Audio Synthesis +4

A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning

1 code implementation NeurIPS 2019 Nicolas Carion, Gabriel Synnaeve, Alessandro Lazaric, Nicolas Usunier

While centralized reinforcement learning methods can optimally solve small MAC instances, they do not scale to large problems and they fail to generalize to scenarios different from those seen during training.

Multi-agent Reinforcement Learning reinforcement-learning +4

Projected Canonical Decomposition for Knowledge Base Completion

no code implementations25 Sep 2019 Timothée Lacroix, Guillaume Obozinski, Joan Bruna, Nicolas Usunier

However, as we show in this paper through experiments on standard benchmarks of link prediction in knowledge bases, ComplEx, a variant of CP, achieves similar performances to recent approaches based on Tucker decomposition on all operating points in terms of number of parameters.

Knowledge Base Completion Link Prediction

Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed

1 code implementation3 Sep 2019 Alexandre Défossez, Nicolas Usunier, Léon Bottou, Francis Bach

We study the problem of source separation for music using deep learning with four known sources: drums, bass, vocals and other accompaniments.

Music Source Separation

Growing Action Spaces

1 code implementation ICML 2020 Gregory Farquhar, Laura Gustafson, Zeming Lin, Shimon Whiteson, Nicolas Usunier, Gabriel Synnaeve

In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress.

reinforcement-learning Reinforcement Learning (RL) +1

Fully Convolutional Speech Recognition

no code implementations17 Dec 2018 Neil Zeghidour, Qiantong Xu, Vitaliy Liptchinsky, Nicolas Usunier, Gabriel Synnaeve, Ronan Collobert

In this paper we present an alternative approach based solely on convolutional neural networks, leveraging recent advances in acoustic models from the raw waveform and language modeling.

Language Modelling speech-recognition +1

To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition

no code implementations9 Dec 2018 Yossi Adi, Neil Zeghidour, Ronan Collobert, Nicolas Usunier, Vitaliy Liptchinsky, Gabriel Synnaeve

In multi-task learning, the goal is speaker prediction; we expect a performance improvement with this joint training if the two tasks of speech recognition and speaker recognition share a common set of underlying features.

Multi-Task Learning Speaker Recognition +2

Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger

1 code implementation ICLR 2018 Gabriel Synnaeve, Zeming Lin, Jonas Gehring, Dan Gant, Vegard Mella, Vasil Khalidov, Nicolas Carion, Nicolas Usunier

We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games.

Starcraft

High-Level Strategy Selection under Partial Observability in StarCraft: Brood War

no code implementations21 Nov 2018 Jonas Gehring, Da Ju, Vegard Mella, Daniel Gant, Nicolas Usunier, Gabriel Synnaeve

We consider the problem of high-level strategy selection in the adversarial setting of real-time strategy games from a reinforcement learning perspective, where taking an action corresponds to switching to the respective strategy.

reinforcement-learning Reinforcement Learning (RL) +2

SING: Symbol-to-Instrument Neural Generator

1 code implementation NeurIPS 2018 Alexandre Défossez, Neil Zeghidour, Nicolas Usunier, Léon Bottou, Francis Bach

On the generalization task of synthesizing notes for pairs of pitch and instrument not seen during training, SING produces audio with significantly improved perceptual quality compared to a state-of-the-art autoencoder based on WaveNet as measured by a Mean Opinion Score (MOS), and is about 32 times faster for training and 2, 500 times faster for inference.

Audio Synthesis Music Generation

End-to-End Speech Recognition From the Raw Waveform

1 code implementation19 Jun 2018 Neil Zeghidour, Nicolas Usunier, Gabriel Synnaeve, Ronan Collobert, Emmanuel Dupoux

In this paper, we study end-to-end systems trained directly from the raw waveform, building on two alternatives for trainable replacements of mel-filterbanks that use a convolutional architecture.

speech-recognition Speech Recognition

Value Propagation Networks

no code implementations ICLR 2018 Nantas Nardelli, Gabriel Synnaeve, Zeming Lin, Pushmeet Kohli, Philip H. S. Torr, Nicolas Usunier

We present Value Propagation (VProp), a set of parameter-efficient differentiable planning modules built on Value Iteration which can successfully be trained using reinforcement learning to solve unseen tasks, has the capability to generalize to larger map sizes, and can learn to navigate in dynamic environments.

Navigate reinforcement-learning +2

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.

Attribute

Learning Filterbanks from Raw Speech for Phone Recognition

2 code implementations3 Nov 2017 Neil Zeghidour, Nicolas Usunier, Iasonas Kokkinos, Thomas Schatz, Gabriel Synnaeve, Emmanuel Dupoux

We train a bank of complex filters that operates on the raw waveform and is fed into a convolutional neural network for end-to-end phone recognition.

Dense and Low-Rank Gaussian CRFs Using Deep Embeddings

no code implementations ICCV 2017 Siddhartha Chandra, Nicolas Usunier, Iasonas Kokkinos

In this work we introduce a structured prediction model that endows the Deep Gaussian Conditional Random Field (G-CRF) with a densely connected graph structure.

Human Part Segmentation Saliency Prediction +3

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.

Attribute

Parseval Networks: Improving Robustness to Adversarial Examples

1 code implementation ICML 2017 Moustapha Cisse, Piotr Bojanowski, Edouard Grave, Yann Dauphin, Nicolas Usunier

We introduce Parseval networks, a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1.

Improving Neural Language Models with a Continuous Cache

14 code implementations13 Dec 2016 Edouard Grave, Armand Joulin, Nicolas Usunier

We propose an extension to neural network language models to adapt their prediction to the recent history.

Language Modelling

TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games

2 code implementations1 Nov 2016 Gabriel Synnaeve, Nantas Nardelli, Alex Auvolat, Soumith Chintala, Timothée Lacroix, Zeming Lin, Florian Richoux, Nicolas Usunier

We present TorchCraft, a library that enables deep learning research on Real-Time Strategy (RTS) games such as StarCraft: Brood War, by making it easier to control these games from a machine learning framework, here Torch.

BIG-bench Machine Learning Starcraft

How should we evaluate supervised hashing?

1 code implementation21 Sep 2016 Alexandre Sablayrolles, Matthijs Douze, Hervé Jégou, Nicolas Usunier

Hashing produces compact representations for documents, to perform tasks like classification or retrieval based on these short codes.

General Classification Retrieval +1

Large-scale Simple Question Answering with Memory Networks

3 code implementations5 Jun 2015 Antoine Bordes, Nicolas Usunier, Sumit Chopra, Jason Weston

Training large-scale question answering systems is complicated because training sources usually cover a small portion of the range of possible questions.

 Ranked #1 on Question Answering on WebQuestions (F1 metric)

Question Answering Transfer Learning

Theory of Optimizing Pseudolinear Performance Measures: Application to F-measure

no code implementations1 May 2015 Shameem A Puthiya Parambath, Nicolas Usunier, Yves GRANDVALET

We study the theoretical properties of a subset of non-linear performance measures called pseudo-linear performance measures which includes $F$-measure, \emph{Jaccard Index}, among many others.

Classification General Classification +3

Open Question Answering with Weakly Supervised Embedding Models

no code implementations16 Apr 2014 Antoine Bordes, Jason Weston, Nicolas Usunier

Building computers able to answer questions on any subject is a long standing goal of artificial intelligence.

Open-Ended Question Answering

Translating Embeddings for Modeling Multi-relational Data

8 code implementations NeurIPS 2013 Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko

We consider the problem of embedding entities and relationships of multi-relational data in low-dimensional vector spaces.

Link Prediction

Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction

no code implementations EMNLP 2013 Jason Weston, Antoine Bordes, Oksana Yakhnenko, Nicolas Usunier

This paper proposes a novel approach for relation extraction from free text which is trained to jointly use information from the text and from existing knowledge.

Relation Relation Extraction

Irreflexive and Hierarchical Relations as Translations

no code implementations26 Apr 2013 Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko

We consider the problem of embedding entities and relations of knowledge bases in low-dimensional vector spaces.

A Transductive Bound for the Voted Classifier with an Application to Semi-supervised Learning

no code implementations NeurIPS 2008 Massih Amini, Nicolas Usunier, François Laviolette

In this case, we propose a second bound on the joint probability that the voted classifier makes an error over an example having its margin over a fixed threshold.

Self-Learning

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