Explore the latest research from Meta

All Publications

December 17, 2018
Huichan Zhao, Aftab M. Hussain, Mihai Duduta, Daniel M. Vogt, Robert J. Wood, David R. Clarke

The design and fabrication of a rolled dielectric elastomer actuator is described and the parametric dependence of the displacement and blocked force on the actuator geometry, elastomer layer thickness, voltage, and number of turns is analyzed.

December 14, 2018
Ahmed Aly, Kushal Lakhotia, Shicong Zhao, Mrinal Mohit, Barlas Oğuz, Abhinav Arora, Sonal Gupta, Christopher Dewan, Stef Nelson-Lindall, Rushin Shah

We introduce PyText – a deep learning based NLP modeling framework built on PyTorch. PyText addresses the often-conflicting requirements of enabling rapid experimentation and of serving models at scale.

December 11, 2018

Product-adoption scenarios are often theoretically modeled as “influence-maximization” (IM) problems, where people influence one another to adopt and the goal is to find a limited set of people to “seed” so as to maximize long-term adoption. In many IM models, if there is no budgetary limit on seeding, the optimal approach involves seeding everybody immediately. Here, we argue that this approach can lead to suboptimal outcomes for “social products” that allow people to communicate with one another.

December 8, 2018
Jigar Doshi, Saikat Basu, Guan Pang

The use of satellite imagery has become increasingly popular for disaster monitoring and response. After a disaster, it is important to prioritize rescue operations, disaster response and coordinate relief efforts. These have to be carried out in a fast and efficient manner since resources are often limited in disaster affected areas and it’s extremely important to identify the areas of maximum damage. However, most of the existing disaster mapping efforts are manual which is time-consuming and often leads to erroneous results.

December 8, 2018
Daniel A. Roberts

We derive a simple and model-independent formula for the change in the generalization gap due to a gradient descent update. We then compare the change in the test error for stochastic gradient descent to the change in test error from an equivalent number of gradient descent updates and show explicitly that stochastic gradient descent acts to regularize generalization error by decorrelating nearby updates.

December 7, 2018
Beliz Gokkaya, Jessica Ai, Michael Tingley, Yonglong Zhang, Ning Dong, Thomas Jiang, Anitha Kubendran, Arun Kumar

In this study, we present HackPPL as a probabilistic programming language in Facebook’s server-side language, Hack. One of the aims of our language is to support deep probabilistic modeling by providing a flexible interface for composing deep neural networks with encoded uncertainty and a rich inference engine.

December 6, 2018
Thomas George, Cesar Laurent, Xavier Bouthillier, Nicolas Ballas, Pascal Vincent

Optimization algorithms that leverage gradient covariance information, such as variants of natural gradient descent (Amari, 1998), offer the prospect of yielding more effective descent directions. For models with many parameters, the covariance matrix they are based on becomes gigantic, making them inapplicable in their original form.