CaltechAUTHORS
  A Caltech Library Service

Discriminative Cooperative Networks for Detecting Phase Transitions

Liu, Ye-Hua and van Nieuwenburg, Evert P. L. (2018) Discriminative Cooperative Networks for Detecting Phase Transitions. Physical Review Letters, 120 (17). Art. No. 176401. ISSN 0031-9007. http://resolver.caltech.edu/CaltechAUTHORS:20180426-142653150

[img] PDF - Published Version
See Usage Policy.

430Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20180426-142653150

Abstract

The classification of states of matter and their corresponding phase transitions is a special kind of machine-learning task, where physical data allow for the analysis of new algorithms, which have not been considered in the general computer-science setting so far. Here we introduce an unsupervised machine-learning scheme for detecting phase transitions with a pair of discriminative cooperative networks (DCNs). In this scheme, a guesser network and a learner network cooperate to detect phase transitions from fully unlabeled data. The new scheme is efficient enough for dealing with phase diagrams in two-dimensional parameter spaces, where we can utilize an active contour model—the snake—from computer vision to host the two networks. The snake, with a DCN “brain,” moves and learns actively in the parameter space, and locates phase boundaries automatically.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1103/PhysRevLett.120.176401DOIArticle
Additional Information:© 2018 American Physical Society. (Received 16 October 2017; published 26 April 2018) The authors thank L. Wang, S. D. Huber, S. Trebst, K. Hepp, M. Sigrist, and T. M. Rice for reading the manuscript and helpful suggestions. Y.-H. L. thanks G. Sordi and A.-M. Tremblay for stimulating discussions. Y.-H.L. is supported by ERC Advanced Grant SIMCOFE and the Canada First Research Excellence Fund. E. P. L. v. N. gratefully acknowledges financial support from the Swiss National Science Foundation (SNSF) through Grant No. P2EZP2-172185. The authors used TensorFlow [58] for machine learning.
Group:Institute for Quantum Information and Matter, IQIM
Funders:
Funding AgencyGrant Number
European Research Council (ERC)SIMCOFE
Canada First Research Excellence FundUNSPECIFIED
Swiss National Science Foundation (SNSF)P2EZP2-172185
Record Number:CaltechAUTHORS:20180426-142653150
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20180426-142653150
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:86065
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:27 Apr 2018 16:15
Last Modified:27 Apr 2018 16:15

Repository Staff Only: item control page