paper-with-me

Papers

Bayesian Meta Sampling for Fast Uncertainty Adaptation

2020-05-01 · ICLR 2020 1 · Zhenyi Wang, Yang Zhao, Ping Yu, Ruiyi Zhang, Changyou Chen

Meta learning has been making impressive progress for fast model adaptation. However, limited work has been done on learning fast uncertainty adaption for Bayesian modeling. In this paper, we propose to achieve the goal by placing meta learning on the space of probability measures, inducing the concept of meta sampling for fast uncertainty adaption. Specifically, we propose a Bayesian meta sampling framework consisting of two main components: a meta sampler and a sample adapter. The meta sampler is constructed by adopting a neural-inverse-autoregressive-flow (NIAF) structure, a variant of the recently proposed neural autoregressive flows, to efficiently generate meta samples to be adapted. The sample adapter moves meta samples to task-specific samples, based on a newly proposed and general Bayesian sampling technique, called optimal-transport Bayesian sampling. The combination of the two components allows a simple learning procedure for the meta sampler to be developed, which can be efficiently optimized via standard back-propagation. Extensive experimental results demonstrate the efficiency and effectiveness of the proposed framework, obtaining better sample quality and faster uncertainty adaption compared to related methods.

📄 PDF Abstract BibTeX

Code (1)

zheshiyige/meta-sampling 공식 구현 pytorch

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

Bayesian Model-Agnostic Meta-Learning

2018-06-11 · NeurIPS 2018 12 · Taesup Kim, Jaesik Yoon, Ousmane Dia, Sungwoong Kim 외

Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper, we propose a novel Bayesian model-agnost…

Active Learningimage-classificationImage ClassificationMeta-Learning+3

Bayesian Meta-reinforcement Learning for Traffic Signal Control

2020-10-01 · Yayi Zou, Zhiwei Qin

In recent years, there has been increasing amount of interest around meta reinforcement learning methods for traffic signal control, which have achieved better performance compared with traditional control methods. Howev…

Continual LearningMeta-LearningMeta Reinforcement Learningreinforcement-learning+3

Gradient-EM Bayesian Meta-learning

2020-06-21 · NeurIPS 2020 12 · Yayi Zou, Xiaoqi Lu

Bayesian meta-learning enables robust and fast adaptation to new tasks with uncertainty assessment. The key idea behind Bayesian meta-learning is empirical Bayes inference of hierarchical model. In this work, we extend t…

Computational EfficiencyFew-Shot Image Classificationimage-classificationImage Classification+2

MALIBO: Meta-learning for Likelihood-free Bayesian Optimization

2023-07-07 · Jiarong Pan, Stefan Falkner, Felix Berkenkamp, Joaquin Vanschoren

Bayesian optimization (BO) is a popular method to optimize costly black-box functions. While traditional BO optimizes each new target task from scratch, meta-learning has emerged as a way to leverage knowledge from relat…

Bayesian OptimizationMeta-Learning

First, Learn What You Don't Know: Active Information Gathering for Driving at the Limits of Handling

2024-10-31 · Alexander Davydov, Franck Djeumou, Marcus Greiff, Makoto Suminaka 외

Combining data-driven models that adapt online and model predictive control (MPC) has enabled effective control of nonlinear systems. However, when deployed on unstable systems, online adaptation may not be fast enough t…

FrictionMeta-LearningModel Predictive Control