Uncertainty Quantification

505 papers with code • 0 benchmarks • 0 datasets

This task has no description! Would you like to contribute one?


Use these libraries to find Uncertainty Quantification models and implementations

Most implemented papers

Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules

klicperajo/dimenet 28 Nov 2020

Many important tasks in chemistry revolve around molecules during reactions.

Uncertainty Sets for Image Classifiers using Conformal Prediction

aangelopoulos/conformal-classification ICLR 2021

Convolutional image classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, hindering their deployment in consequential settings.

Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness

google/uncertainty-baselines NeurIPS 2020

Bayesian neural networks (BNN) and deep ensembles are principled approaches to estimate the predictive uncertainty of a deep learning model.

Rule-based Bayesian regression

themisbo/Rule-based-Bayesian-regr 2 Aug 2020

We introduce a novel rule-based approach for handling regression problems.

COMBO: Conservative Offline Model-Based Policy Optimization

yihaosun1124/OfflineRL-Kit NeurIPS 2021

We overcome this limitation by developing a new model-based offline RL algorithm, COMBO, that regularizes the value function on out-of-support state-action tuples generated via rollouts under the learned model.

Deep Deterministic Uncertainty: A Simple Baseline

omegafragger/DDU 23 Feb 2021

Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive.

A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification

aangelopoulos/conformal-prediction 15 Jul 2021

Conformal prediction is a user-friendly paradigm for creating statistically rigorous uncertainty sets/intervals for the predictions of such models.

Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting

BruceBinBoxing/Deep_Learning_Weather_Forecasting 22 Dec 2018

We cast the weather forecasting problem as an end-to-end deep learning problem and solve it by proposing a novel negative log-likelihood error (NLE) loss function.

Deep learning observables in computational fluid dynamics

kjetil-lye/learning_airfoils 7 Mar 2019

Under the assumption that the underlying neural networks generalize well, we prove that the deep learning MC and QMC algorithms are guaranteed to be faster than the baseline (quasi-) Monte Carlo methods.

Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels

BayesWatch/deep-kernel-transfer NeurIPS 2020

Recently, different machine learning methods have been introduced to tackle the challenging few-shot learning scenario that is, learning from a small labeled dataset related to a specific task.