Fast Amortized Inference and Learning in Log-linear Models with Randomly Perturbed Nearest Neighbor Search

Inference in log-linear models scales linearly in the size of output space in the worst-case. This is often a bottleneck in natural language processing and computer vision tasks when the output space is feasibly enumerable but very large. We propose a method to perform inference in log-linear models...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Mussmann, Stephen, Levy, Daniel, Ermon, Stefano
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 11.07.2017
Subjects
Computer Science - Learning
Computer vision
Data structures
Inference
Natural language processing
Random variables
Statistics - Machine Learning
Online AccessGet full text

Cover

More Information
Summary:Inference in log-linear models scales linearly in the size of output space in the worst-case. This is often a bottleneck in natural language processing and computer vision tasks when the output space is feasibly enumerable but very large. We propose a method to perform inference in log-linear models with sublinear amortized cost. Our idea hinges on using Gumbel random variable perturbations and a pre-computed Maximum Inner Product Search data structure to access the most-likely elements in sublinear amortized time. Our method yields provable runtime and accuracy guarantees. Further, we present empirical experiments on ImageNet and Word Embeddings showing significant speedups for sampling, inference, and learning in log-linear models.
ISSN:2331-8422
DOI:10.48550/arxiv.1707.03372