skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Machine Learning Out-of-Equilibrium Phases of Matter

Abstract

Neural-network-based machine learning is emerging as a powerful tool for obtaining phase diagrams when traditional regression schemes using local equilibrium order parameters are not available, as in many-body localized (MBL) or topological phases. Nevertheless, instances of machine learning offering new insights have been rare up to now. Here we show that a single feed-forward neural network can decode the defining structures of two distinct MBL phases and a thermalizing phase, using entanglement spectra obtained from individual eigenstates. For this, we introduce a simplicial geometry-based method for extracting multipartite phase boundaries. We find that this method outperforms conventional metrics for identifying MBL phase transitions, revealing a sharper phase boundary and shedding new insight on the topology of the phase diagram. Furthermore, the phase diagram we acquire from a single disorder configuration confirms that the machine-learning-based approach we establish here can enable speedy exploration of large phase spaces that can assist with the discovery of new MBL phases. To our knowledge, this Letter represents the first example of a standard machine learning approach revealing new information on phase transitions.

Authors:
 [1];  [2];  [1]
  1. Cornell Univ., Ithaca, NY (United States). Dept. of Physics
  2. Harvard Univ., Cambridge, MA (United States). Dept. of Physics
Publication Date:
Research Org.:
Cornell Univ., Ithaca, NY (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES)
OSTI Identifier:
1541329
Alternate Identifier(s):
OSTI ID: 1456267
Grant/Contract Number:  
SC0010313
Resource Type:
Journal Article: Accepted Manuscript
Journal Name:
Physical Review Letters
Additional Journal Information:
Journal Volume: 120; Journal Issue: 25; Journal ID: ISSN 0031-9007
Publisher:
American Physical Society (APS)
Country of Publication:
United States
Language:
English
Subject:
75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND SUPERFLUIDITY

Citation Formats

Venderley, Jordan, Khemani, Vedika, and Kim, Eun-Ah. Machine Learning Out-of-Equilibrium Phases of Matter. United States: N. p., 2018. Web. doi:10.1103/physrevlett.120.257204.
Venderley, Jordan, Khemani, Vedika, & Kim, Eun-Ah. Machine Learning Out-of-Equilibrium Phases of Matter. United States. https://doi.org/10.1103/physrevlett.120.257204
Venderley, Jordan, Khemani, Vedika, and Kim, Eun-Ah. 2018. "Machine Learning Out-of-Equilibrium Phases of Matter". United States. https://doi.org/10.1103/physrevlett.120.257204. https://www.osti.gov/servlets/purl/1541329.
@article{osti_1541329,
title = {Machine Learning Out-of-Equilibrium Phases of Matter},
author = {Venderley, Jordan and Khemani, Vedika and Kim, Eun-Ah},
abstractNote = {Neural-network-based machine learning is emerging as a powerful tool for obtaining phase diagrams when traditional regression schemes using local equilibrium order parameters are not available, as in many-body localized (MBL) or topological phases. Nevertheless, instances of machine learning offering new insights have been rare up to now. Here we show that a single feed-forward neural network can decode the defining structures of two distinct MBL phases and a thermalizing phase, using entanglement spectra obtained from individual eigenstates. For this, we introduce a simplicial geometry-based method for extracting multipartite phase boundaries. We find that this method outperforms conventional metrics for identifying MBL phase transitions, revealing a sharper phase boundary and shedding new insight on the topology of the phase diagram. Furthermore, the phase diagram we acquire from a single disorder configuration confirms that the machine-learning-based approach we establish here can enable speedy exploration of large phase spaces that can assist with the discovery of new MBL phases. To our knowledge, this Letter represents the first example of a standard machine learning approach revealing new information on phase transitions.},
doi = {10.1103/physrevlett.120.257204},
url = {https://www.osti.gov/biblio/1541329}, journal = {Physical Review Letters},
issn = {0031-9007},
number = 25,
volume = 120,
place = {United States},
year = {Thu Jun 21 00:00:00 EDT 2018},
month = {Thu Jun 21 00:00:00 EDT 2018}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 77 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Quantum Entanglement in Neural Network States
journal, May 2017


Local Conservation Laws and the Structure of the Many-Body Localized States
journal, September 2013


Localization-protected quantum order
journal, July 2013


Equivalence of restricted Boltzmann machines and tensor network states
journal, February 2018


Machine learning quantum phases of matter beyond the fermion sign problem
journal, August 2017


On Many-Body Localization for Quantum Spin Chains
journal, April 2016


Universal Dynamics and Renormalization in Many-Body-Localized Systems
journal, March 2015


Absence of Diffusion in Certain Random Lattices
journal, March 1958


Observation of discrete time-crystalline order in a disordered dipolar many-body system
journal, March 2017


Many-body localization edge in the random-field Heisenberg chain
journal, February 2015


Average entropy of a subsystem
journal, August 1993


Floquet Time Crystals
journal, August 2016


Probing many-body localization with neural networks
journal, June 2017


Localization and topology protected quantum coherence at the edge of hot matter
journal, July 2015


Many-body localization and thermalization: Insights from the entanglement spectrum
journal, May 2016


Critical Properties of the Many-Body Localization Transition
journal, April 2017


Discovering phase transitions with unsupervised learning
journal, November 2016


Machine learning topological states
journal, November 2017


Criterion for Many-Body Localization-Delocalization Phase Transition
journal, December 2015


Learning phase transitions by confusion
journal, February 2017


Many-Body Localization in a Disordered Quantum Ising Chain
journal, September 2014


Solving the quantum many-body problem with artificial neural networks
journal, February 2017


Nonlocal adiabatic response of a localized system to local manipulations
journal, June 2015


Machine learning phases of matter
journal, February 2017


Area laws in a many-body localized state and its implications for topological order
journal, September 2013


Many-body localization and symmetry-protected topological order
journal, April 2014


Self-learning Monte Carlo method
journal, January 2017


Many-body localization phase transition
journal, November 2010


Localization of interacting fermions at high temperature
journal, April 2007


Many-body localization in the Heisenberg X X Z magnet in a random field
journal, February 2008


Low-frequency conductivity in many-body localized systems
journal, September 2015


Machine learning Z 2 quantum spin liquids with quasiparticle statistics
journal, December 2017


Critical behavior of random transverse-field Ising spin chains
journal, March 1995


Two Universality Classes for the Many-Body Localization Transition
journal, August 2017


Metal–insulator transition in a weakly interacting many-electron system with localized single-particle states
journal, May 2006


Characterizing the many-body localization transition using the entanglement spectrum
journal, November 2017


Absolute stability and spatiotemporal long-range order in Floquet systems
journal, August 2016


Phase Structure of Driven Quantum Systems
journal, June 2016


Universal Properties of Many-Body Delocalization Transitions
journal, September 2015


Theory of the Many-Body Localization Transition in One-Dimensional Systems
journal, September 2015


Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
journal, December 2016


Many-Body Localization and Thermalization in Quantum Statistical Mechanics
journal, March 2015


Quantum revivals and many-body localization
journal, April 2015


Bimodal entanglement entropy distribution in the many-body localization transition
journal, November 2016


Machine learning: Trends, perspectives, and prospects
journal, July 2015


Quantum Loop Topography for Machine Learning
journal, May 2017


Hilbert-Glass Transition: New Universality of Temperature-Tuned Many-Body Dynamical Quantum Criticality
journal, March 2014


Stability and instability towards delocalization in many-body localization systems
journal, April 2017


Phenomenology of fully many-body-localized systems
journal, November 2014


Observation of a discrete time crystal
journal, March 2017


The Roles of Plastic Surgeons in Advancing Artificial Intelligence in Plastic Surgery
journal, April 2021


Probing many-body localization with neural networks
text, January 2017


The many-body localization phase transition
text, January 2010


Phenomenology of fully many-body-localized systems
text, January 2014


Many-body localization edge in the random-field Heisenberg chain
text, January 2014


Non-local Adiabatic Response of a Localized System to Local Manipulations
text, January 2014


Universal properties of many-body delocalization transitions
text, January 2015


Low-frequency conductivity in many-body localized systems
text, January 2015


A criterion for many-body localization-delocalization phase transition
text, January 2015


Many body localization and thermalization: insights from the entanglement spectrum
text, January 2016


Machine learning phases of matter
text, January 2016


Critical Properties of the Many-Body Localization Transition
text, January 2016


Observation of a Discrete Time Crystal
text, January 2016


Machine Learning Topological States
text, January 2016


Learning phase transitions by confusion
text, January 2016


Self-Learning Monte Carlo Method
text, January 2016


Quantum Entanglement in Neural Network States
text, January 2017


Two universality classes for the many-body localization transition
text, January 2017


Works referencing / citing this record:

Inverse design of photonic topological state via machine learning
journal, May 2019


Learning epidemic threshold in complex networks by Convolutional Neural Network
journal, November 2019


Machine learning the many-body localization transition in random spin systems
journal, September 2018


Machine learning algorithms based on generalized Gibbs ensembles
journal, October 2018


From DFT to machine learning: recent approaches to materials science–a review
journal, May 2019


Unsupervised learning eigenstate phases of matter
journal, August 2019


Two-dimensional frustrated J 1 J 2 model studied with neural network quantum states
journal, September 2019


Multifaceted machine learning of competing orders in disordered interacting systems
journal, October 2019


Deep learning topological invariants of band insulators
journal, August 2018


Many-body localization and delocalization in large quantum chains
journal, November 2018


Deep learning and the AdS / CFT correspondence
journal, August 2018


Machine learning dynamical phase transitions in complex networks
journal, November 2019


Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
journal, February 2019


Machine learning of phase transitions in the percolation and X Y models
journal, March 2019


Symmetries and Many-Body Excitations with Neural-Network Quantum States
journal, October 2018


Machine Learning Many-Body Localization: Search for the Elusive Nonergodic Metal
journal, December 2018


Extrapolating Quantum Observables with Machine Learning: Inferring Multiple Phase Transitions from Properties of a Single Phase
journal, December 2018


Butterfly effect in interacting Aubry-Andre model: Thermalization, slow scrambling, and many-body localization
journal, December 2019


Machine learning and the physical sciences
journal, December 2019


Symmetries and Many-Body Excitations with Neural-Network Quantum States
text, January 2018


Many-body localization and delocalization in large quantum chains
text, January 2018


Deep Learning Topological Invariants of Band Insulators
text, January 2018


Unsupervised Learning Eigenstate Phases of Matter
text, January 2019


A high-bias, low-variance introduction to Machine Learning for physicists
journal, May 2019


Many-body localization, symmetry and topology
journal, July 2018


Probing criticality in quantum spin chains with neural networks
journal, August 2020


Many-body localization and delocalization in large quantum chains
journal, November 2018


Extending machine learning classification capabilities with histogram reweighting
journal, September 2020


Mapping distinct phase transitions to a neural network
journal, November 2020


Analyzing Nonequilibrium Quantum States through Snapshots with Artificial Neural Networks
journal, October 2021


Casimir effect with machine learning
journal, September 2020


Unsupervised learning of topological phase transitions using the Calinski-Harabaz index
journal, January 2021


Adding machine learning within Hamiltonians: Renormalization group transformations, symmetry breaking and restoration
journal, February 2021