Learning Restricted Boltzmann Machines with greedy quantum search

TL;DR

This paper introduces quantum algorithms for learning the structure of Restricted Boltzmann Machines, achieving polynomial speedups over classical methods, and extends prior work to the quantum computing domain.

Contribution

It extends structure learning of RBMs to quantum algorithms, providing polynomial speedups for ferromagnetic and locally consistent RBMs.

Findings

Quantum algorithms outperform classical in structure learning

Polynomial speedup achieved over classical algorithms

Applicable to ferromagnetic and locally consistent RBMs

Abstract

Restricted Boltzmann Machines (RBMs) are widely used probabilistic undirected graphical models with visible and latent nodes, playing an important role in statistics and machine learning. The task of structure learning for RBMs involves inferring the underlying graph by using samples from the visible nodes. Specifically, learning the two-hop neighbors of each visible node allows for the inference of the graph structure. Prior research has addressed the structure learning problem for specific classes of RBMs, namely ferromagnetic and locally consistent RBMs. In this paper, we extend the scope to the quantum computing domain and propose corresponding quantum algorithms for this problem. Our study demonstrates that the proposed quantum algorithms yield a polynomial speedup compared to the classical algorithms for learning the structure of these two classes of RBMs.