Stochastic gradient method with accelerated stochastic dynamics

Research output: Contribution to journalConference articlepeer-review

4 Citations (Scopus)


We implement the simple method to accelerate the convergence speed to the steady state and enhance the mixing rate to the stochastic gradient Langevin method. The ordinary stochastic gradient method is based on mini-batch learning for reducing the computational cost when the amount of data is extraordinary large. The stochasticity of the gradient can be mitigated by the injection of Gaussian noise, which yields the stochastic Langevin gradient method; this method can be used for Bayesian posterior sampling. However, the performance of the stochastic Langevin gradient method depends on the mixing rate of the stochastic dynamics. In this study, we propose violating the detailed balance condition to enhance the mixing rate. Recent studies have revealed that violating the detailed balance condition accelerates the convergence to a stationary state and reduces the correlation time between the samplings. We implement this violation of the detailed balance condition in the stochastic gradient Langevin method and test our method for a simple model to demonstrate its performance.

Original languageEnglish
Article number012019
JournalJournal of Physics: Conference Series
Issue number1
Publication statusPublished - 2016 Apr 6
EventInternational Meeting on High-Dimensional Data-Driven Science, HD3 2015 - Kyoto, Japan
Duration: 2015 Dec 142015 Dec 17


Dive into the research topics of 'Stochastic gradient method with accelerated stochastic dynamics'. Together they form a unique fingerprint.

Cite this