Bayesian Optimization Based on Meta Learning with Neural Process
-
- KAWANO Makoto
- The University of Tokyo
-
- KUMAGAI Wataru
- RIKEN AIP
-
- MATSUI Kota
- RIKEN AIP
-
- IWASAWA Yusuke
- The University of Tokyo
-
- MATUSO Yutaka
- The University of Tokyo
Bibliographic Information
- Other Title
-
- Neural Process によるメタ学習にもとづくベイズ最適化
Abstract
<p>Bayesian optimization is a technique that optimizes the black box function based on a probabilistic model with a few observation points as possible. In this study, we consider Bayesian optimization in a situation where similar functions other than the target function to be evaluated can be accessed at a low cost. In this paper, we propose BONP using neural processes (NPs), a deep generation model considering the uncertainty of prediction, as a surrogate model. Although NPs can be used for meta-learning, it often ignores given observations and causes under-fitting. To avoid this issue, we also propose a new Dot-CNP that maps observation points to function space and apply it to BONP. In experiments, we dealt with the regression problem with the 1d-synthetic function and the Bayesian optimization problem with the three types of acquisition functions, and demonstrated the effectiveness of the proposed method.</p>
Journal
-
- Proceedings of the Annual Conference of JSAI
-
Proceedings of the Annual Conference of JSAI JSAI2020 (0), 2J1GS202-2J1GS202, 2020
The Japanese Society for Artificial Intelligence
- Tweet
Details 詳細情報について
-
- CRID
- 1390003825189419136
-
- NII Article ID
- 130007856974
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- CiNii Articles
-
- Abstract License Flag
- Disallowed