.png){kind=icon}
.png){kind=icon}
Return
Machine-learning-assisted Monte Carlo fails at sampling computationally hard problems
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/acbe91.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Several strategies have been recently proposed in order to improve Monte Carlo sampling efficiency using machine learning tools. Here, we challenge these methods by considering a class of problems that are known to be exponentially hard to sample using conventional local Monte Carlo at low enough temperatures. In particular, we study the antiferromagnetic Potts model on a random graph, which reduces to the coloring of random graphs at zero temperature. We test several machine-learning-assisted Monte Carlo approaches, and we find that they all fail. Our work thus provides good benchmarks for future proposals for smart sampling algorithms.
Keywords:
statistical physics
Monte Carlo Markov Chains
sampling
Journal
M
IF:
4.6
Papers:
1.1K
Citations:
3.4K