PofoliaShared via Pofolia

Statistical Papers· 2026Q2

Fast replica exchange stochastic gradient Langevin dynamics

Guanxun Li, Guang Lin, Zecheng Zhang, Quan Zhou

Short summary

A new method expedites replica exchange stochastic gradient Langevin dynamics (SGLD) by directly estimating the bias from stochastic gradient estimators, allowing high-temperature chains to be simulated at negligible cost and preserving convergence.

AI-generated from the title and abstract; the full text is not read.

TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways, key points and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Field: Statistics and Probability

Statistics and ProbabilityMathematics