Rare-Event Detection by Quasi-Wang-Landau Monte Carlo Sampling with Approximate Bayesian Computation
- Authors
- Kwon, Junseok
- Issue Date
- Nov-2019
- Publisher
- SPRINGER
- Keywords
- Rare-event detection; Wang-Landau Monte Carlo; Approximate Bayesian computation; Halton sequence
- Citation
- JOURNAL OF MATHEMATICAL IMAGING AND VISION, v.61, no.9, pp 1258 - 1275
- Pages
- 18
- Journal Title
- JOURNAL OF MATHEMATICAL IMAGING AND VISION
- Volume
- 61
- Number
- 9
- Start Page
- 1258
- End Page
- 1275
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/38698
- DOI
- 10.1007/s10851-019-00906-y
- ISSN
- 0924-9907
1573-7683
- Abstract
- We propose a new rare-event detection method based on quasi-Wang-Landau Monte Carlo (QWLMC) sampling with approximate Bayesian computation (ABC) called QWLMC-ABC. QWLMC-ABC integrates ABC and a Halton sequence into Wang-Landau Monte Carlo (WLMC) sampling methods. The Halton sequence provides an improved proposal function and increases the accuracy of WLMC sampling, which results in QWLMC sampling. ABC approximates a likelihood function and boosts the speed of QWLMC sampling, which yields QWLMC-ABC. QWLMC-ABC is applied to estimate the rareness of events in a statistical manner. Experimental results demonstrate that our method is comparable to state-of-the-art methods. Compared with sampling-based approaches including WLMC and QWLMC sampling, QWLMC-ABC localizes rare events at a fraction of the computation time.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/38698)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.