Explore the latest research from Facebook

All Publications

January 15, 2021 Sarah Bechtle, Artem Molchanov, Yevgen Chebotar, Edward Grefenstette, Ludovic Righetti, Gaurav S. Sukhatme, Franziska Meier
Paper

Meta Learning via Learned Loss

In this paper, we take the first step towards automating this process, with the view of producing models which train faster and more robustly. Concretely, we present a meta-learning method for learning parametric loss functions that can generalize across different tasks and model architectures.
Paper
December 16, 2020 Matteo Castiglioni, Andrea Celli, Alberto Marchesi, Nicola Gatti
Paper

Online Bayesian Persuasion

In Bayesian persuasion, an informed sender has to design a signaling scheme that discloses the right amount of information so as to influence the behavior of a self-interested receiver. This kind of strategic interaction is ubiquitous in real-world economic scenarios. However, the seminal model by Kamenica and Gentzkow makes some stringent assumptions that limit its applicability in practice.
Paper
December 15, 2020 Stéphane d'Ascoli, Levent Sagun, Giulio Biroli
Paper

Triple descent and the two kinds of overfitting: Where & why do they appear?

A recent line of research has highlighted the existence of a “double descent” phenomenon in deep learning, whereby increasing the number of training examples N causes the generalization error of neural networks to peak when N is of the same order as the number of parameters P. In earlier works, a similar phenomenon was shown to exist in simpler models such as linear regression, where the peak instead occurs when N is equal to the input dimension D. Since both peaks coincide with the interpolation threshold, they are often conflated in the literature. In this paper, we show that despite their apparent similarity, these two scenarios are inherently different.
Paper
December 8, 2020 Ankit Arun, Soumya Batra, Vikas Bhardwaj, Ashwini Challa, Pinar Donmez, Peyman Heidari, Hakan Inan, Shashank Jain, Anuj Kumar, Shawn Mei, Karthik Mohan, Michael White
Paper

Best Practices for Data-Efficient Modeling in NLG: How to Train Production-Ready Neural Models with Less Data

In this paper, we present approaches that have helped us deploy data-efficient neural solutions for NLG in conversational systems to production. We describe a family of sampling and modeling techniques to attain production quality with light-weight neural network models using only a fraction of the data that would be necessary otherwise, and show a thorough comparison between each.
Paper
December 7, 2020 Terrance DeVries, Michal Drozdzal, Graham Taylor
Paper

Instance Selection for GANs

In this work we propose a novel approach to improve sample quality: altering the training dataset via instance selection before model training has taken place. By refining the empirical data distribution before training, we redirect model capacity towards high-density regions, which ultimately improves sample fidelity, lowers model capacity requirements, and significantly reduces training time.
Paper
December 7, 2020 Edward J. Smith, Roberto Calandra, Adriana Romero, Georgia Gkioxari, David Meger, Jitendra Malik, Michal Drozdzal
Paper

3D Shape Reconstruction from Vision and Touch

When a toddler is presented a new toy, their instinctual behaviour is to pick it up and inspect it with their hand and eyes in tandem, clearly searching over its surface to properly understand what they are playing with. At any instance here, touch provides high fidelity localized information while vision provides complementary global context. However, in 3D shape reconstruction, the complementary fusion of visual and haptic modalities remains largely unexplored. In this paper, we study this problem and present an effective chart-based approach to multi-modal shape understanding which encourages a similar fusion vision and touch information.
Paper
December 7, 2020 Maximilian Nickel, Brian Karrer, Daniel Jiang, Sam Daulton, Ben Letham, Andrew Gordon Wilson, Eytan Bakshy
Paper

BOTORCH: A Framework for Efficient Monte-Carlo Bayesian Optimization

We introduce BOTORCH, a modern programming framework for Bayesian optimization that combines Monte-Carlo (MC) acquisition functions, a novel sample average approximation optimization approach, auto-differentiation, and variance reduction techniques.
Paper
December 7, 2020 Shali Jiang, Daniel Jiang, Max Balandat, Brian Karrer, Jacob R. Gardner, Roman Garnett
Paper

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

In this paper, we provide the first efficient implementation of general multi-step lookahead Bayesian optimization, formulated as a sequence of nested optimization problems within a multi-step scenario tree.
Paper
December 6, 2020 Yann Dubois, Douwe Kiela, David J. Schwab, Ramakrishna Vedantam
Paper

Learning Optimal Representations with the Decodable Information Bottleneck

We propose the Decodable Information Bottleneck (DIB) that considers information retention and compression from the perspective of the desired predictive family. As a result, DIB gives rise to representations that are optimal in terms of expected test performance and can be estimated with guarantees.
Paper
December 6, 2020 Xian Li, Asa Cooper Stickland, Yuqing Tang, Xiang Kong
Paper

Deep Transformers with Latent Depth

The Transformer model has achieved state-of-the-art performance in many sequence modeling tasks. However, how to leverage model capacity with large or variable depths is still an open challenge. We present a probabilistic framework to automatically learn which layer(s) to use by learning the posterior distributions of layer selection.
Paper