Abstract | ||
---|---|---|
Recent theoretical analyses reveal that existing Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) methods need large mini-batches of samples (exponentially dependent on the dimension) to reduce the mean square error of gradient estimates and ensure non-asymptotic convergence guarantees when the target distribution has a nonconvex potential function. In this paper, we propose a novel SG-MCMC algorithm, called Hybrid Stochastic Gradient Hamiltonian Monte Carlo (HSG-HMC) method, which needs merely one sample per iteration and possesses a simple structure with only one hyperparameter. Such improvement leverages a hybrid stochastic gradient estimator that exploits historical stochastic gradient information to control the mean square error. Theoretical analyses show that our method obtains the best-known overall sample complexity to achieve epsilon-accuracy in terms of the 2-Wasserstein distance for sampling from distributions with nonconvex potential functions. Empirical studies on both simulated and real-world datasets demonstrate the advantage of our method. |
Year | Venue | DocType |
---|---|---|
2021 | THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | Conference |
Volume | ISSN | Citations |
35 | 2159-5399 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chao Zhang | 1 | 8 | 5.49 |
Zhijian Li | 2 | 2 | 3.41 |
Zebang Shen | 3 | 17 | 9.36 |
Jiahao Xie | 4 | 0 | 2.03 |
Hui Qian | 5 | 59 | 13.26 |