Journal
JOURNAL OF PHYSICS-CONDENSED MATTER
Volume 30, Issue 39, Pages -Publisher
IOP PUBLISHING LTD
DOI: 10.1088/1361-648X/aaddc6
Keywords
many-body localization transition; energy spectrum; machine learning
Categories
Funding
- National Basic Research Program of China [2015CB921101]
- National Natural Science Foundation of China [11674282]
Ask authors/readers for more resources
The transition between thermal and many-body localized phases in isolated random spin systems are typically identified by the distribution of nearest level spacings. In this work, by employing machine learning methodology, we show this transition can be learnt through raw energy spectrum without any pre-processing. After achieving so in conventional random spin chain with differentiable level spacing distributions, we further construct novel models with misleading signatures of level spacing, and show machine can defeat the latter when training data is raw energy spectrum. Our work shows the low-level energy spectrum contains more information than level spacings, and can be captured by machine in a direct while efficient way, which makes it a promising new tool for studying a variety of isolated quantum systems.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available