Maximum-Entropy Inference with a Programmable Annealer


Loading...

Date

2016-03-03

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Optimisation problems typically involve finding the ground state (i.e. the minimum energy configuration) of a cost function with respect to many variables. If the variables are corrupted by noise then this maximises the likelihood that the solution is correct. The maximum entropy solution on the other hand takes the form of a Boltzmann distribution over the ground and excited states of the cost function to correct for noise. Here we use a programmable annealer for the information decoding problem which we simulate as a random Ising model in a field. We show experimentally that finite temperature maximum entropy decoding can give slightly better bit-error-rates than the maximum likelihood approach, confirming that useful information can be extracted from the excited states of the annealer. Furthermore we introduce a bit-by-bit analytical method which is agnostic to the specific application and use it to show that the annealer samples from a highly Boltzmann-like distribution. Machines of this kind are therefore candidates for use in a variety of machine learning applications which exploit maximum entropy inference, including language processing and image recognition.

Publication status

published

Editor

Book title

Volume

6

Pages / Article No.

22318

Publisher

Nature

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Information theory and computation; Mathematics and computing; Quantum information

Organisational unit

Notes

Funding

Related publications and datasets