Search Results for author:
Found 54 papers, 25 papers with code
Code Llama: Open Foundation Models for Code
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.
Ranked #15 on
Code Generation
on HumanEval
Towards Reliable Assessments of Demographic Disparities in Multi-Label Image Classifiers
These metrics successfully incentivized performance improvements on person-centric tasks such as face analysis and are used to understand risks of modern models.
Leveraging Demonstrations with Latent Space Priors
Starting with a learned joint latent space, we separately train a generative model of demonstration sequences and an accompanying low-level policy.
Contextual bandits with concave rewards, and an application to fair ranking
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.
Fast online ranking with fairness of exposure
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.
Measuring and signing fairness as performance under multiple stakeholder distributions
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.
Optimizing generalized Gini indices for fairness in rankings
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 Indicators for Systematic Assessments of Visual Feature Extractors
Systematic diagnosis of fairness, harms, and biases of computer vision systems is an important step towards building socially responsible systems.
Two-sided fairness in rankings via Lorenz dominance
Our experiments also show that it increases the utility of the worse-off at lower costs in terms of overall utility.
Hierarchical Skills for Efficient Exploration
We alleviate the need for prior knowledge by proposing a hierarchical skill learning framework that acquires skills of varying complexity in an unsupervised manner.
Online Selection of Diverse Committees
Citizens' assemblies need to represent subpopulations according to their proportions in the general population.
Online certification of preference-based fairness for personalized recommender systems
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.
Gradient Matching for Domain Generalization
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.
A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings
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.
Meta-Reinforcement Learning With Informed Policy Regularization
Meta-reinforcement learning aims at finding a policy able to generalize to new environments.
On ranking via sorting by estimated expected utility
We provide an answer to this question in the form of a structural characterization of ranking losses for which a suitable regression is consistent.
End-to-End Object Detection with Transformers
We present a new method that views object detection as a direct set prediction problem.
Ranked #20 on
Panoptic Segmentation
on COCO minival
Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization
We test the performance of our algorithm in a variety of environments where tasks may vary within each episode.
Tensor Decompositions for temporal knowledge base completion
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.
Ranked #1 on
Link Prediction
on YAGO15k
A Simple Convergence Proof of Adam and Adagrad
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
Source separation for music is the task of isolating contributions, or stems, from different instruments recorded individually and arranged together to form a song.
Ranked #3 on
Multi-task Audio Source Seperation
on MTASS
A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning
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
+3
Projected Canonical Decomposition for Knowledge Base Completion
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.
Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed
We study the problem of source separation for music using deep learning with four known sources: drums, bass, vocals and other accompaniments.
Growing Action Spaces
In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress.
Fully Convolutional Speech Recognition
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.
Ranked #3 on
Speech Recognition
on WSJ eval93
To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognition
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.
Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger
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.
High-Level Strategy Selection under Partial Observability in StarCraft: Brood War
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.
SING: Symbol-to-Instrument Neural Generator
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.
Canonical Tensor Decomposition for Knowledge Base Completion
The problem of Knowledge Base Completion can be framed as a 3rd-order binary tensor completion problem.
Ranked #2 on
Link Prediction
on FB15k
End-to-End Speech Recognition From the Raw Waveform
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.
Value Propagation Networks
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.
Fader Networks:Manipulating Images by Sliding Attributes
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 Filterbanks from Raw Speech for Phone Recognition
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
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.
Fader Networks: Manipulating Images by Sliding Attributes
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.
Parseval Networks: Improving Robustness to Adversarial Examples
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
We propose an extension to neural network language models to adapt their prediction to the recent history.
Ranked #32 on
Language Modelling
on WikiText-2
(using extra training data)
TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games
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.
How should we evaluate supervised hashing?
Hashing produces compact representations for documents, to perform tasks like classification or retrieval based on these short codes.
Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
We consider scenarios from the real-time strategy game StarCraft as new benchmarks for reinforcement learning algorithms.
Large-scale Simple Question Answering with Memory Networks
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)
Combining Two And Three-Way Embeddings Models for Link Prediction in Knowledge Bases
This paper tackles the problem of endogenous link prediction for Knowledge Base completion.
Theory of Optimizing Pseudolinear Performance Measures: Application to F-measure
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.
Optimizing F-Measures by Cost-Sensitive Classification
We present a theoretical analysis of F-measures for binary, multiclass and multilabel classification.
Open Question Answering with Weakly Supervised Embedding Models
Building computers able to answer questions on any subject is a long standing goal of artificial intelligence.
Ranked #1 on
Question Answering
on Reverb
Robust Bloom Filters for Large MultiLabel Classification Tasks
This paper presents an approach to multilabel classification (MLC) with a large number of labels.
Translating Embeddings for Modeling Multi-relational Data
We consider the problem of embedding entities and relationships of multi-relational data in low-dimensional vector spaces.
Ranked #5 on
Link Prediction
on FB122
Connecting Language and Knowledge Bases with Embedding Models for Relation Extraction
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.
Irreflexive and Hierarchical Relations as Translations
We consider the problem of embedding entities and relations of knowledge bases in low-dimensional vector spaces.
Learning from Multiple Partially Observed Views - an Application to Multilingual Text Categorization
We assume the existence of view generating functions which may complete the missing views in an approximate way.
A Transductive Bound for the Voted Classifier with an Application to Semi-supervised Learning
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.
