$Δ$-UQ: Accurate Uncertainty Quantification via Anchor Marginalization
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Model OptimizationOut-of-Distribution DetectionUncertainty QuantificationSimilar Papers 제목 키워드 기반
Language Model Uncertainty Quantification with Attention Chain
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+2Bayesian Evidential Deep Learning with PAC Regularization
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 QuantificationFully Bayesian VIB-DeepSSM
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 InferenceA Kernel Framework to Quantify a Model's Local Predictive Uncertainty under Data Distributional Shifts
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 QuantificationBayesian Uncertainty Quantification with Anchored Ensembles for Robust EV Power Consumption Prediction
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 …