CUED Publications database

Stochastic inference for scalable probabilistic modeling of binary matrices

Hernández-Lobato, JM and Houlsby, N and Ghahramani, Z (2014) Stochastic inference for scalable probabilistic modeling of binary matrices. In: UNSPECIFIED pp. 1693-1710..

Full text not available from this repository.

Abstract

Copyright © (2014) by the International Machine Learning Society (IMLS) All rights reserved. Fully observed large binary matrices appear in a wide variety of contexts. To model them, probabilistic matrix factorization (PMF) methods are an attractive solution. However, current batch algorithms for PMF can be inefficient because they need to analyze the entire data matrix before producing any parameter updates. We derive an efficient stochastic inference algorithm for PMF models of fully observed binary matrices. Our method exhibits faster convergence rates than more expensive batch approaches and has better predictive performance than scalable alternatives. The proposed method includes new data subsampling strategies which produce large gains over standard uniform subsampling. We also address the task of automatically selecting the size of the minibatches of data used by our method. For this, we derive an algorithm that adjusts this hyper-parameter online.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:45
Last Modified: 14 Sep 2017 01:27
DOI: