paper-with-me

홈 › Papers

Representing Model Uncertainty of Neural Networks in Sparse Information Form

2019-09-25 · JongSeok Lee, Rudolph Triebel

This paper addresses the problem of representing a system's belief using multi-variate normal distributions (MND) where the underlying model is based on a deep neural network (DNN). The major challenge with DNNs is the computational complexity that is needed to obtain model uncertainty using MNDs. To achieve a scalable method, we propose a novel approach that expresses the parameter posterior in sparse information form. Our inference algorithm is based on a novel Laplace Approximation scheme, which involves a diagonal correction of the Kronecker-factored eigenbasis. As this makes the inversion of the information matrix intractable - an operation that is required for full Bayesian analysis, we devise a low-rank approximation of this eigenbasis and a memory-efficient sampling scheme. We provide both a theoretical analysis and an empirical evaluation on various benchmark data sets, showing the superiority of our approach over existing methods.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Form

Similar Papers 제목 키워드 기반

Uncertainty Weighted Causal Graphs

2020-02-02 · Eduardo C. Garrido-Merchán, C. Puente, A. Sobrino, J. A. Olivas

Causality has traditionally been a scientific way to generate knowledge by relating causes to effects. From an imaginery point of view, causal graphs are a helpful tool for representing and infering new causal informatio…

Management

Improving the Gaussian Process Sparse Spectrum Approximation by Representing Uncertainty in Frequency Inputs

2015-03-09 · Yarin Gal, Richard Turner

Standard sparse pseudo-input approximations to the Gaussian process (GP) cannot handle complex functions well. Sparse spectrum alternatives attempt to answer this but are known to over-fit. We suggest the use of variatio…

Variational Inference

EUBRL: Epistemic Uncertainty Directed Bayesian Reinforcement Learning

2025-12-17 · Jianfei Ma, Wee Sun Lee arxiv

At the boundary between the known and the unknown, an agent inevitably confronts the dilemma of whether to explore or to exploit. Epistemic uncertainty reflects such boundaries, representing systematic uncertainty due to…

Reinforcement Learning

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

2015-06-06 · Yarin Gal, Zoubin Ghahramani

Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematical…

Bayesian InferenceDeep Reinforcement LearningGaussian ProcessesGeneral Classification+3

Estimating Model Uncertainty of Neural Network in Sparse Information Form

2020-01-01 · ICML 2020 1 · Jongseok Lee, Matthias Humt, Jianxiang Feng, Rudolph Triebel

We present a sparse representation of model uncertainty for Deep Neural Networks (DNNs) where the parameter posterior is approximated with an inverse formulation of the Multivariate Normal Distribution (MND), also known …

Dimensionality ReductionForm