paper-with-me

Papers

$Δ$-UQ: Accurate Uncertainty Quantification via Anchor Marginalization

2021-10-05 · Rushil Anirudh, Jayaraman J. Thiagarajan

We present $\Delta$-UQ -- a novel, general-purpose uncertainty estimator using the concept of anchoring in predictive models. Anchoring works by first transforming the input into a tuple consisting of an anchor point drawn from a prior distribution, and a combination of the input sample with the anchor using a pretext encoding scheme. This encoding is such that the original input can be perfectly recovered from the tuple -- regardless of the choice of the anchor. Therefore, any predictive model should be able to predict the target response from the tuple alone (since it implicitly represents the input). Moreover, by varying the anchors for a fixed sample, we can estimate uncertainty in the prediction even using only a single predictive model. We find this uncertainty is deeply connected to improper sampling of the input data, and inherent noise, enabling us to estimate the total uncertainty in any system. With extensive empirical studies on a variety of use-cases, we demonstrate that $\Delta$-UQ outperforms several competitive baselines. Specifically, we study model fitting, sequential model optimization, model based inversion in the regression setting and out of distribution detection, & calibration under distribution shifts for classification.

📄 PDF Abstract BibTeX arXiv:2110.02197

Code (0)

등록된 구현이 없습니다.

Tasks

Model OptimizationOut-of-Distribution DetectionUncertainty Quantification

Similar Papers 제목 키워드 기반

Language Model Uncertainty Quantification with Attention Chain

2025-03-24 · Yinghao Li, Rushi Qiang, Lama Moukheiber, Chao Zhang

Accurately quantifying a large language model's (LLM) predictive uncertainty is crucial for judging the reliability of its answers. While most existing research focuses on short, directly answerable questions with closed…

Computational EfficiencyLanguage ModelingLanguage Modellingmodel+2

Bayesian Evidential Deep Learning with PAC Regularization

2019-06-03 · pproximateinference AABI Symposium 2021 1 · Manuel Haussmann, Sebastian Gerwinn, Melih Kandemir

We propose a novel method for closed-form predictive distribution modeling with neural nets. In quantifying prediction uncertainty, we build on Evidential Deep Learning, which has been impactful as being both simple to i…

Deep LearningUncertainty Quantification

Fully Bayesian VIB-DeepSSM

2023-05-09 · Jadie Adams, Shireen Elhabian

Statistical shape modeling (SSM) enables population-based quantitative analysis of anatomical shapes, informing clinical diagnosis. Deep learning approaches predict correspondence-based SSM directly from unsegmented 3D i…

AnatomyUncertainty QuantificationVariational Inference

A Kernel Framework to Quantify a Model's Local Predictive Uncertainty under Data Distributional Shifts

2021-03-02 · Rishabh Singh, Jose C. Principe

Traditional Bayesian approaches for model uncertainty quantification rely on notoriously difficult processes of marginalization over each network parameter to estimate its probability density function (PDF). Our hypothes…

Uncertainty Quantification

Bayesian Uncertainty Quantification with Anchored Ensembles for Robust EV Power Consumption Prediction

2025-11-09 · Ghazal Farhani, Taufiq Rahman, Kieran Humphries arxiv

Accurate EV power estimation underpins range prediction and energy management, yet practitioners need both point accuracy and trustworthy uncertainty. We propose an anchored-ensemble Long Short-Term Memory (LSTM) with a …