paper-with-me

홈 › Papers

Conservative Uncertainty Estimation By Fitting Prior Networks

2020-05-01 · ICLR 2020 1 · Kamil Ciosek, Vincent Fortuin, Ryota Tomioka, Katja Hofmann, Richard Turner

Obtaining high-quality uncertainty estimates is essential for many applications of deep neural networks. In this paper, we theoretically justify a scheme for estimating uncertainties, based on sampling from a prior distribution. Crucially, the uncertainty estimates are shown to be conservative in the sense that they never underestimate a posterior uncertainty obtained by a hypothetical Bayesian algorithm. We also show concentration, implying that the uncertainty estimates converge to zero as we get more data. Uncertainty estimates obtained from random priors can be adapted to any deep network architecture and trained using standard supervised learning pipelines. We provide experimental evaluation of random priors on calibration and out-of-distribution detection on typical computer vision tasks, demonstrating that they outperform deep ensembles in practice.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Detection

Methods 이 논문이 사용한 방법론

Deep Ensembles 설명 없음

Similar Papers 제목 키워드 기반

COMBO: Conservative Offline Model-Based Policy Optimization

2021-02-16 · NeurIPS 2021 12 · Tianhe Yu, Aviral Kumar, Rafael Rafailov, Aravind Rajeswaran 외

Model-based algorithms, which learn a dynamics model from logged experience and perform some sort of pessimistic planning under the learned model, have emerged as a promising paradigm for offline reinforcement learning (…

modelOffline RLUncertainty Quantification

DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning

2023-09-16 · Xiao-Yin Liu, Xiao-Hu Zhou, Mei-Jiang Gui, Xiao-Liang Xie 외

Model-based reinforcement learning (RL), which learns environment model from offline dataset and generates more out-of-distribution model data, has become an effective approach to the problem of distribution shift in off…

D4RLmodelModel-based Reinforcement LearningOffline RL+3

Pointwise uncertainty quantification for sparse variational Gaussian process regression with a Brownian motion prior

2023-09-29 · NeurIPS 2023 11

We study pointwise estimation and uncertainty quantification for a sparse variational Gaussian process method with eigenvector inducing variables. For a rescaled Brownian motion prior, we derive theoretical guarantees an…

Uncertainty Quantification

Uncertainty-Aware Bayes' Rule and Its Applications

2023-11-09 · Shixiong Wang

Bayes' rule has enabled innumerable powerful algorithms of statistical signal processing and statistical machine learning. However, when model misspecifications exist in prior and/or data distributions, the direct applic…

Philosophy

Deep Model-Based Reinforcement Learning via Estimated Uncertainty and Conservative Policy Optimization

2019-11-28 · Qi Zhou, Houqiang Li, Jie Wang

Model-based reinforcement learning algorithms tend to achieve higher sample efficiency than model-free methods. However, due to the inevitable errors of learned models, model-based methods struggle to achieve the same as…

Model-based Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)