Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration
Published Online:22 Oct 2021https://doi.org/10.1287/opre.2021.2162
- Cited by
- 1 April 2026 | Foundations of Computational Mathematics, Vol. 180
- Physica D: Nonlinear Phenomena, Vol. 483
- 18 May 2025 | Mathematics, Vol. 13, No. 10
- IEEE Transactions on Neural Networks and Learning Systems, Vol. 36, No. 4
- IEEE Transactions on Automation Science and Engineering, Vol. 22
- Foundations of Data Science, Vol. 7, No. <![CDATA[4]]>
- 7 June 2023 | Mathematical Programming, Vol. 205, No. 1-2
- Electronic Journal of Probability, Vol. 29, No. none
- Advances in Applied Mathematics, Vol. 13, No. 02
- 20 June 2023 | Machine Learning, Vol. 112, No. 8
- Stochastic Processes and their Applications, Vol. 146
Volume 70, Issue 5
September-October 2022
Pages iii-vi, 2597-3033, C2-C3
Article Information
Supplemental Material
Metrics
Information
- Received:August 21, 2019
- Accepted:April 06, 2021
- Published Online:October 22, 2021
Copyright © 2021, INFORMS
Cite as
Xuefeng Gao, Mert Gürbüzbalaban, Lingjiong Zhu (2021) Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration. Operations Research 70(5):2931-2947.
https://doi.org/10.1287/opre.2021.2162
Keywords
The authors thank the area editor, the associate editor, and an anonymous referee for helpful comments and suggestions. They also thank Agostino Capponi, Xiuli Chao, Wenbin Chen, Jim Dai, Murat A. Erdogdu, Qi Feng, Fuqing Gao, Jianqiang Hu, Jin Ma, Sanjoy Mitter, Asuman Ozdaglar, Pablo Parrilo, Umut Şimşekli, and S. R. S. Varadhan for helpful discussions. The authors are listed in alphabetical order.
