Skip to main content

Stochastic gradient hamiltonian monte carlo methods with recursive variance reduction

Publication ,  Conference
Zou, D; Xu, P; Gu, Q
Published in: Advances in Neural Information Processing Systems
January 1, 2019

Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) algorithms have received increasing attention in both theory and practice. In this paper, we propose a Stochastic Recursive Variance-Reduced gradient HMC (SRVR-HMC) algorithm. It makes use of a semi-stochastic gradient estimator that recursively accumulates the gradient information to reduce the variance of the stochastic gradient. We provide a convergence analysis of SRVR-HMC for sampling from a class of non-log-concave distributions and show that SRVR-HMC converges faster than all existing HMC-type algorithms based on underdamped Langevin dynamics. Thorough experiments on synthetic and real-world datasets validate our theory and demonstrate the superiority of SRVR-HMC.

Duke Scholars

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2019

Volume

32

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zou, D., Xu, P., & Gu, Q. (2019). Stochastic gradient hamiltonian monte carlo methods with recursive variance reduction. In Advances in Neural Information Processing Systems (Vol. 32).
Zou, D., P. Xu, and Q. Gu. “Stochastic gradient hamiltonian monte carlo methods with recursive variance reduction.” In Advances in Neural Information Processing Systems, Vol. 32, 2019.
Zou D, Xu P, Gu Q. Stochastic gradient hamiltonian monte carlo methods with recursive variance reduction. In: Advances in Neural Information Processing Systems. 2019.
Zou, D., et al. “Stochastic gradient hamiltonian monte carlo methods with recursive variance reduction.” Advances in Neural Information Processing Systems, vol. 32, 2019.
Zou D, Xu P, Gu Q. Stochastic gradient hamiltonian monte carlo methods with recursive variance reduction. Advances in Neural Information Processing Systems. 2019.

Published In

Advances in Neural Information Processing Systems

ISSN

1049-5258

Publication Date

January 1, 2019

Volume

32

Related Subject Headings

  • 4611 Machine learning
  • 1702 Cognitive Sciences
  • 1701 Psychology