Variational Deterministic Uncertainty Quantification

2021-01-01 · Joost van Amersfoort, Lewis Smith, Andrew Jesson, Oscar Key, Yarin Gal

Building on recent advances in uncertainty quantification using a single deep deterministic model (DUQ), we introduce variational Deterministic Uncertainty Quantification (vDUQ). We overcome several shortcomings of DUQ by recasting it as a Gaussian process (GP) approximation. Our principled approximation is based on a inducing point GP in combination with Deep Kernel Learning. This enables vDUQ to use rigorous probabilistic foundations, and work not only on classification but also on regression problems. We avoid uncertainty collapse away from the training data by regularizing the spectral norm of the deep feature extractor. Our method matches SotA accuracy, 96.2% on CIFAR-10, while maintaining the speed of softmax models, and provides uncertainty estimates competitive with Deep Ensembles. We demonstrate our method in regression problems and by estimating uncertainty in causal inference for personalized medicine.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Causal Inference regressionUncertainty Quantification

Methods 이 논문이 사용한 방법론

Deep Ensembles 설명 없음

Causal inference Causal inference is the process of drawing a conclusion about a causal connection based on the conditions of the occurrence of an effect. The main difference between causal…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Enhanced uncertainty quantification variational autoencoders for the solution of Bayesian inverse problems

2025-02-18 · Andrea Tonini, Luca Dede'

Among other uses, neural networks are a powerful tool for solving deterministic and Bayesian inverse problems in real-time. In the Bayesian framework, variational autoencoders, a specialized type of neural network, enabl…

Uncertainty Quantification

Alpha-VI DeepONet: A prior-robust variational Bayesian approach for enhancing DeepONets with uncertainty quantification

2024-08-01 · Soban Nasir Lone, Subhayan De, Rajdip Nayek

We introduce a novel deep operator network (DeepONet) framework that incorporates generalised variational inference (GVI) using R\'enyi's $\alpha$-divergence to learn complex operators while quantifying uncertainty. By i…

Operator learning Uncertainty Quantification Variational Inference

Bayesian 3D Steerable CNNs: Enabling Equivariance and Uncertainty Quantification Simultaneously

2026-06-13 · Abhishek Keripale, Ponkrshnan Thiagarajan, Susanta Ghosh arxiv

Steerable convolutional neural networks (Steerable-CNNs) guarantee SE(3)-equivariance by parameterizing kernels as linear combinations of steerable basis functions, but their deterministic nature precludes uncertainty qu…

Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing

2023-06-11 · NeurIPS 2023 11 · Ziyan Wang, Hao Wang

Existing regression models tend to fall short in both accuracy and uncertainty estimation when the label distribution is imbalanced. In this paper, we propose a probabilistic deep learning model, dubbed variational imbal…

Probabilistic Deep Learning regression Uncertainty Quantification

Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval

2020-11-25 · ICCV 2021 10 · Frederik Warburg, Martin Jørgensen, Javier Civera, Søren Hauberg

Uncertainty quantification in image retrieval is crucial for downstream decisions, yet it remains a challenging and largely unexplored problem. Current methods for estimating uncertainties are poorly calibrated, computat…

Computational Efficiency Image Retrieval Retrieval Triplet+1