Transductive Boltzmann Machines
Machine Learning
2018-05-22 v1 Machine Learning
Abstract
We present transductive Boltzmann machines (TBMs), which firstly achieve transductive learning of the Gibbs distribution. While exact learning of the Gibbs distribution is impossible by the family of existing Boltzmann machines due to combinatorial explosion of the sample space, TBMs overcome the problem by adaptively constructing the minimum required sample space from data to avoid unnecessary generalization. We theoretically provide bias-variance decomposition of the KL divergence in TBMs to analyze its learnability, and empirically demonstrate that TBMs are superior to the fully visible Boltzmann machines and popularly used restricted Boltzmann machines in terms of efficiency and effectiveness.
Cite
@article{arxiv.1805.07938,
title = {Transductive Boltzmann Machines},
author = {Mahito Sugiyama and Koji Tsuda and Hiroyuki Nakahara},
journal= {arXiv preprint arXiv:1805.07938},
year = {2018}
}
Comments
10 pages, 1 figure, 2 tables