533 Results
July 10, 2018
Modeling Others using Oneself in Multi-Agent Reinforcement Learning
International Conference on Machine Learning (ICML)
We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility.
By: Roberta Raileanu, Emily Denton, Arthur Szlam, Rob Fergus
Machine Learning July 9, 2018
Experience developing and deploying concurrency analysis at Facebook
Static Analysis Symposium
This paper tells the story of the development of RacerD, a static program analysis for detecting data races that is in production at Facebook. The technical details of RacerD are described in a separate paper; we concentrate here on how the project unfolded from a human point of view.
By: Peter O'Hearn
Systems & Networking July 9, 2018
Continuous Reasoning: Scaling the Impact of Formal Methods
Logic in Computer Science
This paper describes work in continuous reasoning, where formal reasoning about a (changing) codebase is done in a fashion which mirrors the iterative, continuous model of software development that is increasingly practiced in industry. We suggest that advances in continuous reasoning will allow formal reasoning to scale to more programs, and more programmers.
By: Peter O'HearnJuly 9, 2018
Mixed batches and symmetric discriminators for GAN training
International Conference on Machine Learning (ICML)
We propose to feed the discriminator with mixed batches of true and fake samples, and train it to predict the ratio of true samples in the batch.
By: Thomas Lucas, Corentin Tallec, Jakob Verbeek, Yann Ollivier
Facebook AI Research July 9, 2018
Composable Planning with Attributes
International Conference on Machine Learning (ICML)
We propose a method that learns a policy for transitioning between “nearby” sets of attributes, and maintains a graph of possible transitions.
By: Amy Zhang, Adam Lerer, Sainbayar Sukhbaatar, Rob Fergus, Arthur Szlam
Facebook AI Research July 7, 2018
Reconstructing Scenes with Mirror and Glass Surfaces
ACM SIGGRAPH
We introduce a fully automatic pipeline that allows us to reconstruct the geometry and extent of planar glass and mirror surfaces while being able to distinguish between the two.
By: Thomas Whelan, Michael Goesele, Steven J. Lovegrove, Julian Straub, Simon Green, Richard Szeliski, Steven Butterfield, Shobhit Verma, Richard Newcombe
AR/VR
Computer Vision July 7, 2018
Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations
arXiv
We show that the gradient descent algorithm provides an implicit regularization effect in the learning of over-parameterized matrix factorization models and one-hidden-layer neural networks with quadratic activations.
By: Yuanzhi Li, Tengyu Ma, Hongyang ZhangJuly 1, 2018
We Need a Testability Transformation Semantics
16th International Conference on Software Engineering and Formal Methods
This paper briefly reviews Testability Transformation, its formal definition, and the open problem of constructing a set of formal test adequacy semantics to underpin the current practice of deploying transformations to help testing and verification activities.
By: Mark Harman
Systems & Networking June 29, 2018
Understanding the Loss Surface of Neural Networks for Binary Classification
International Conference on Machine Learning (ICML)
Here we focus on the training performance of neural networks for binary classification, and provide conditions under which the training error is zero at all local minima of appropriately chosen surrogate loss functions.
By: Shiyu Liang, Ruoyu Sun, Yixuan Li, R. SrikantJune 28, 2018
Hardware Remediation At Scale
International Conference on Dependable Systems and Networks (DSN)
Large scale services have automated hardware remediation to maintain the infrastructure availability at a healthy level. In this paper, we share the current remediation flow at Facebook, and how it is being monitored.
By: Fan (Fred) Lin, Matt Beadon, Harish Dattatraya Dixit, Gautham Vunnam, Amol Desai, Sriram Sankar
Data Science