Metropolis-Hastings MCMC with dual mini-batches and reversible SGLD proposal
Abstract/Contents
- Abstract
- Traditional MCMC algorithms are computationally intensive and do not scale well to large data. In particular, the Metropolis-Hastings (MH) algorithm requires passing over the entire dataset to evaluate the likelihood ratio in each iteration. We propose a general framework for performing MH-MCMC using dual mini-batches (MHDB) of the whole dataset each time and show that this gives rise to approximately a tempered stationary distribution. We prove that MHDB preserves the modes of the original target distribution and derive an error bound on the approximation with mild assumptions on the likelihood. To further extend the utility of the algorithm to high dimensional settings, we construct a proposal with forward and reverse moves using stochastic gradient and show that the construction leads to reasonable acceptance probabilities. We demonstrate the performance of our algorithm in both low dimensional models and high dimensional neural network applications. Particularly in the latter case, compared to popular optimization methods, our method is more robust to the choice of learning rate and improves testing accuracy.
Description
Type of resource | text |
---|---|
Form | electronic resource; remote; computer; online resource |
Extent | 1 online resource. |
Place | California |
Place | [Stanford, California] |
Publisher | [Stanford University] |
Copyright date | 2019; ©2019 |
Publication date | 2019; 2019 |
Issuance | monographic |
Language | English |
Creators/Contributors
Author | Wu, Tung-yu | |
---|---|---|
Degree supervisor | Wong, Wing Hung | |
Thesis advisor | Wong, Wing Hung | |
Thesis advisor | Owen, Art B | |
Thesis advisor | Ye, Yinyu | |
Degree committee member | Owen, Art B | |
Degree committee member | Ye, Yinyu | |
Associated with | Stanford University, Institute for Computational and Mathematical Engineering. |
Subjects
Genre | Theses |
---|---|
Genre | Text |
Bibliographic information
Statement of responsibility | Tung-yu Wu. |
---|---|
Note | Submitted to the Institute for Computational and Mathematical Engineering. |
Thesis | Thesis Ph.D. Stanford University 2019. |
Location | electronic resource |
Access conditions
- Copyright
- © 2019 by Tung-yu Wu
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...