Publications

Publication

December 08, 2020

NLP

Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming

Motivated by the needs of resource constrained dialog policy learning, we introduce dialog policy via differentiable inductive logic (DILOG).…

Zhenpeng Zhou, Ahmad Beirami Paul Crook, Pararth Shah, Rajen Subba, Alborz Geramifard

December 08, 2020

Read the Paper

Publication

December 08, 2020

NLP

Online Versus Offline NMT Quality: An In-depth Analysis on English–German and German–English

We conduct in this work an evaluation study comparing offline and online neural machine translation architectures.…

Maha Elbayad, Michael Ustaszewski, Emmanuelle Esperança-Rodier, Francis Brunet Manquat, Jakob Verbeek, Laurent Besacier

December 08, 2020

Read the Paper

Publication

December 07, 2020

Joint Policy Search for Collaborative Multi-agent Imperfect Information Games

To learn good joint policies for multi-agent collaboration with imperfect information remains a fundamental challenge. While for two-player zero-sum games, coordinate-ascent approaches…

Stéphane d’Ascoli, Levent Sagun, Giulio Biroli

December 07, 2020

Read the Paper

Publication

December 07, 2020

Adversarial Example Games

The existence of adversarial examples capable of fooling trained neural network classifiers calls for a much better understanding of possible attacks to guide the development…

Avishek Joey Bose, Gauthier Gidel, Andre Cianflone, Pascal Vincent, Simon Lacoste-Julien, William L. Hamilton

December 07, 2020

Read the Paper

Publication

December 07, 2020

BoTorch: A Framework for Efficient Monte-Carlo Bayesian Optimization

Bayesian optimization provides sample-efficient global optimization for a broad range of applications, including automatic machine learning, engineering, physics, and experimental design.…

Maximilian Balandat, Brian Karrer, Daniel R. Jiang, Samuel Daulton, Benjamin Letham, Andrew Gordon Wilson, Eytan Bakshy

December 07, 2020

Read the Paper

Publication

December 07, 2020

Labelling unlabelled videos from scratch with multi-modal self-supervision

A large part of the current success of deep learning lies in the effectiveness of data -- more precisely: labelled data. Yet, labelling a dataset with human annotation continues to carry high costs…

Yuki M. Asano, Mandela Patrick, Christian Rupprecht, Andrea Vedaldi

December 07, 2020

Read the Paper

Publication

December 07, 2020

Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees

Bayesian optimization is a sequential decision making framework for optimizing expensive-to-evaluate black-box functions.…

Shali Jiang, Daniel R. Jiang, Maximilian Balandat, Brian Karrer, Jacob R. Gardner, Roman Garnett

December 07, 2020

Read the Paper

Publication

December 06, 2020

Combining Deep Reinforcement Learning and Search for Imperfect-Information Games

The combination of deep reinforcement learning and search at both training and test time is a powerful paradigm that has led to a number of successes in single-agent…

Noam Brown, Anton Bakhtin, Adam Lerer, Qucheng Gong

December 06, 2020

Read the Paper

Publication

December 06, 2020

Pre-training via Paraphrasing

We introduce MARGE, a pre-trained sequence-to-sequence model learned with an unsupervised multi-lingual multi-document paraphrasing objective.…

Mike Lewis, Marjan Ghazvininejad, Gargi Ghosh, Armen Aghajanyan, Sida Wang, Luke Zettlemoyer

December 06, 2020

Read the Paper

Publication

December 06, 2020

Cross-lingual Retrieval for Iterative Self-Supervised Training

Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models. In this work, we found that the cross-lingual alignment can…

Chau Tran, Yuqing Tang, Xian Li, Jiatao Gu

December 06, 2020

Read the Paper

Publication

December 06, 2020

Self-Supervised Learning by Cross-Modal Audio-Video Clustering

Visual and audio modalities are highly correlated, yet they contain different information. Their strong correlation makes it possible to predict the semantics of one from the other …

Humam Alwassel, Dhruv Mahajan, Bruno Korbar, Lorenzo Torresani, Bernard Ghanem, Du Tran

December 06, 2020

Read the Paper

Publication

December 06, 2020

Neural Dynamic Policies for End-to-End Sensorimotor Learning

The current dominant paradigm in sensorimotor control, whether imitation or reinforcement learning, is to train policies directly in raw action spaces such as torque…