scholar.google.com › citations
This repository contains a PyTorch implementation of paper "Uncertainty Estimation with Infinitesimal Jackknife, Its Distribution and Mean-Field Approximation".
This paper proposes a framework for single-shot predictive uncertainty quantification of a neural network that replaces the conventional Bayesian notion of ...
The main idea is to use infinitesimal jackknife, a classical tool from statistics for uncertainty estimation to construct a pseudo-ensemble that can be ...
Jun 13, 2020 · Abstract:Many methods have been proposed to quantify the predictive uncertainty associated with the outputs of deep neural networks.
Uncertainty estimation with infinitesimal jackknife, its distribution and mean-field approximation. Z Lu, E Ie, F Sha. arXiv preprint arXiv:2006.07584, 2020.
Uncertainty Estimation with Infinitesimal Jackknife, Its Distribution and Mean-Field Approximation · Zhiyun LuEugene IeFei Sha. Computer Science, Mathematics.
The code repository for paper "Uncertainty Estimation with Infinitesimal Jackknife, Its Distribution and Mean-Field Approximation". Sha-Lab/mean-field ...
Uncertainty Estimation with Infinitesimal Jackknife, Its Distribution and Mean-Field Approximation · Zhiyun Lu, Eugene Ie, Fei Sha. 2020 (modified: 06 Nov 2022) ...
Usable estimates of predictive uncertainty should (1) cover the true prediction targets with high probability, and (2) discriminate between high- and low- ...
Missing: Field | Show results with:Field
We now use Bayes' theorem and a mean-field approximation, similarly to (13). ... Uncertainty estimation with infinitesimal jackknife, its distribution and mean- ...