All Research Areas
Research Areas
Year Published

93 Results

July 29, 2018

Online Optical Marker-based Hand Tracking with Deep Labels

Special Interest Group on Computer Graphics and Interactive Techniques (SIGGRAPH)

We propose a technique that frames the labeling problem as a keypoint regression problem conducive to a solution using convolutional neural networks.

By: Shangchen Han, Beibei Liu, Robert Wang, Yuting Ye, Christopher D. Twigg, Kenrick Kin
July 13, 2018

Analyzing Uncertainty in Neural Machine Translation

International Conference on Machine Learning (ICML)

Our study relates some of these issues to the inherent uncertainty of the task, due to the existence of multiple valid translations for a single source sentence, and to the extrinsic uncertainty caused by noisy training data.

By: Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato
July 11, 2018

Convergent TREE BACKUP and RETRACE with Function Approximation

International Conference on Machine Learning (ICML)

In this work, we show that the TREE BACKUP and RETRACE algorithms are unstable with linear function approximation, both in theory and in practice with specific examples.

By: Ahmed Touati, Pierre-Luc Bacon, Doina Precup, Pascal Vincent
July 11, 2018

Learning Diffusion using Hyperparameters

International Conference on Machine Learning (ICML)

In this paper we advocate for a hyperparametric approach to learn diffusion in the independent cascade (IC) model. The sample complexity of this model is a function of the number of edges in the network and consequently learning becomes infeasible when the network is large.

By: Dimitris Kalimeris, Yaron Singer, Karthik Subbian, Udi Weinsberg
July 10, 2018

Optimizing the Latent Space of Generative Networks

International Conference on Machine Learning (ICML)

The goal of this paper is to disentangle the contribution of these two factors to the success of GANs. In particular, we introduce Generative Latent Optimization (GLO), a framework to train deep convolutional generators using simple reconstruction losses.

By: Piotr Bojanowski, Armand Joulin, David Lopez-Paz, Arthur Szlam
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
July 7, 2018

Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations


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 Zhang
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. Srikant
June 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
June 19, 2018

A Generative Adversarial Approach for Zero-Shot Learning from Noisy Texts

Computer Vision and Pattern Recognition (CVPR)

Most existing zero-shot learning methods consider the problem as a visual semantic embedding one. Given the demonstrated capability of Generative Adversarial Networks (GANs) to generate images, we instead leverage GANs to imagine unseen categories from text descriptions and hence recognize novel classes with no examples being seen.

By: Yizhe Zhu, Mohamed Elhoseiny, Bingchen Liu, Xi Peng, Ahmed Elgammal