Stochastic Variance-Reduced Hamilton Monte Carlo Methods
Zou, Difan, Xu, Pan, Gu, Quanquan
We propose a fast stochastic Hamilton Monte Carlo (HMC) method, for sampling from a smooth and strongly log-concave distribution. At the core of our proposed method is a variance reduction technique inspired by the recent advance in stochastic optimization. We show that, to achieve $\epsilon$ accuracy in 2-Wasserstein distance, our algorithm achieves $\tilde O(n+\kappa^{2}d^{1/2}/\epsilon+\kappa^{4/3}d^{1/3}n^{2/3}/\epsilon^{2/3})$ gradient complexity (i.e., number of component gradient evaluations), which outperforms the state-of-the-art HMC and stochastic gradient HMC methods in a wide regime. We also extend our algorithm for sampling from smooth and general log-concave distributions, and prove the corresponding gradient complexity as well. Experiments on both synthetic and real data demonstrate the superior performance of our algorithm.
Oct-18-2020
- Country:
- North America > United States
- California > Los Angeles County > Los Angeles (0.28)
- Europe > Sweden
- Asia
- Middle East > Jordan (0.04)
- Afghanistan > Parwan Province
- Charikar (0.04)
- North America > United States
- Genre:
- Research Report (0.82)
- Technology: