The opaque nature of transformer-based models, particularly in applications susceptible to unethical practices such as dark-patterns in user interfaces, requires models that integrate uncertainty quantification to enhance trust in predictions. This study focuses on dark-pattern detection, deceptive design choices that manipulate user decisions, undermining autonomy and consent. We propose a differential fine-tuning approach implemented at the final classification head via uncertainty quantification with transformer-based pre-trained models. Employing a dense neural network (DNN) head architecture as a baseline, we examine two methods capable of quantifying uncertainty: Spectral-normalized Neural Gaussian Processes (SNGPs) and Bayesian Neural Networks (BNNs). These methods are evaluated on a set of open-source foundational models across multiple dimensions: model performance, variance in certainty of predictions and environmental impact during training and inference phases. Results demonstrate that integrating uncertainty quantification maintains performance while providing insights into challenging instances within the models. Moreover, the study reveals that the environmental impact does not uniformly increase with the incorporation of uncertainty quantification techniques. The study's findings demonstrate that uncertainty quantification enhances transparency and provides measurable confidence in predictions, improving the explainability and clarity of black-box models. This facilitates informed decision-making and mitigates the influence of dark-patterns on user interfaces. These results highlight the importance of incorporating uncertainty quantification techniques in developing machine learning models, particularly in domains where interpretability and trustworthiness are critical.
Satellite optical images, upon their on-ground receipt, offer a distorted view of the observed scene. Their restoration, classically including denoising, deblurring, and sometimes super-resolution, is required before their exploitation. Moreover, quantifying the uncertainty related to this restoration could be valuable by lowering the risk of hallucination and avoiding propagating these biases in downstream applications. Deep learning methods are now state-of-the-art for satellite image restoration. However, they require to train a specific network for each sensor and they do not provide the associated uncertainties. This paper proposes a generic method involving a single network to restore images from several sensors and a scalable way to derive the uncertainties. We focus on deep regularization (DR) methods, which learn a deep prior on target images before plugging it into a model-based optimization scheme. First, we introduce VBLE-xz, which solves the inverse problem in the latent space of a variational compressive autoencoder, estimating the uncertainty jointly in the latent and in the image spaces. It enables scalable posterior sampling with relevant and calibrated uncertainties. Second, we propose the denoiser-based method SatDPIR, adapted from DPIR, which efficiently computes accurate point estimates. We conduct a comprehensive set of experiments on very high resolution simulated and real Pleiades images, asserting both the performance and robustness of the proposed methods. VBLE-xz and SatDPIR achieve state-of-the-art results compared to direct inversion methods. In particular, VBLE-xz is a scalable method to get realistic posterior samples and accurate uncertainties, while SatDPIR represents a compelling alternative to direct inversion methods when uncertainty quantification is not required.
Autonomous and semi-autonomous systems are using deep learning models to improve decision-making. However, deep classifiers can be overly confident in their incorrect predictions, a major issue especially in safety-critical domains. The present study introduces three foundational desiderata for developing real-world risk-aware classification systems. Expanding upon the previously proposed Evidential Deep Learning (EDL), we demonstrate the unity between these principles and EDL's operational attributes. We then augment EDL empowering autonomous agents to exercise discretion during structured decision-making when uncertainty and risks are inherent. We rigorously examine empirical scenarios to substantiate these theoretical innovations. In contrast to existing risk-aware classifiers, our proposed methodologies consistently exhibit superior performance, underscoring their transformative potential in risk-conscious classification strategies.
Uncertainty quantification in text-to-image (T2I) generative models is crucial for understanding model behavior and improving output reliability. In this paper, we are the first to quantify and evaluate the uncertainty of T2I models with respect to the prompt. Alongside adapting existing approaches designed to measure uncertainty in the image space, we also introduce Prompt-based UNCertainty Estimation for T2I models (PUNC), a novel method leveraging Large Vision-Language Models (LVLMs) to better address uncertainties arising from the semantics of the prompt and generated images. PUNC utilizes a LVLM to caption a generated image, and then compares the caption with the original prompt in the more semantically meaningful text space. PUNC also enables the disentanglement of both aleatoric and epistemic uncertainties via precision and recall, which image-space approaches are unable to do. Extensive experiments demonstrate that PUNC outperforms state-of-the-art uncertainty estimation techniques across various settings. Uncertainty quantification in text-to-image generation models can be used on various applications including bias detection, copyright protection, and OOD detection. We also introduce a comprehensive dataset of text prompts and generation pairs to foster further research in uncertainty quantification for generative models. Our findings illustrate that PUNC not only achieves competitive performance but also enables novel applications in evaluating and improving the trustworthiness of text-to-image models.
Large language models (LLMs) have revolutionized the field of natural language processing with their impressive reasoning and question-answering capabilities. However, these models are sometimes prone to generating credible-sounding but incorrect information, a phenomenon known as LLM hallucinations. Reliable uncertainty estimation in LLMs is essential for fostering trust in their generated responses and serves as a critical tool for the detection and prevention of erroneous or hallucinated outputs. To achieve reliable and well-calibrated uncertainty quantification in open-ended and free-form natural language generation, we propose an uncertainty-aware fine-tuning approach for LLMs. This approach enhances the model's ability to provide reliable uncertainty estimates without compromising accuracy, thereby guiding them to produce more trustworthy responses. We introduce a novel uncertainty-aware causal language modeling loss function, grounded in the principles of decision theory. Through rigorous evaluation on multiple free-form question-answering datasets and models, we demonstrate that our uncertainty-aware fine-tuning approach yields better calibrated uncertainty estimates in natural language generation tasks than fine-tuning with the standard causal language modeling loss. Furthermore, the experimental results show that the proposed method significantly improves the model's ability to detect hallucinations and identify out-of-domain prompts.
Optimizing smart grid operations relies on critical decision-making informed by uncertainty quantification, making probabilistic forecasting a vital tool. Designing such forecasting models involves three key challenges: accurate and unbiased uncertainty quantification, workload reduction for data scientists during the design process, and limitation of the environmental impact of model training. In order to address these challenges, we introduce AutoPQ, a novel method designed to automate and optimize probabilistic forecasting for smart grid applications. AutoPQ enhances forecast uncertainty quantification by generating quantile forecasts from an existing point forecast by using a conditional Invertible Neural Network (cINN). AutoPQ also automates the selection of the underlying point forecasting method and the optimization of hyperparameters, ensuring that the best model and configuration is chosen for each application. For flexible adaptation to various performance needs and available computing power, AutoPQ comes with a default and an advanced configuration, making it suitable for a wide range of smart grid applications. Additionally, AutoPQ provides transparency regarding the electricity consumption required for performance improvements. We show that AutoPQ outperforms state-of-the-art probabilistic forecasting methods while effectively limiting computational effort and hence environmental impact. Additionally and in the context of sustainability, we quantify the electricity consumption required for performance improvements.
Reliable uncertainty quantification at unobserved spatial locations, especially in the presence of complex and heterogeneous datasets, remains a core challenge in spatial statistics. Traditional approaches like Kriging rely heavily on assumptions such as normality, which often break down in large-scale, diverse datasets, leading to unreliable prediction intervals. While machine learning methods have emerged as powerful alternatives, they primarily focus on point predictions and provide limited mechanisms for uncertainty quantification. Conformal prediction, a distribution-free framework, offers valid prediction intervals without relying on parametric assumptions. However, existing conformal prediction methods are either not tailored for spatial settings, or existing ones for spatial data have relied on rather restrictive i.i.d. assumptions. In this paper, we propose Localized Spatial Conformal Prediction (LSCP), a conformal prediction method designed specifically for spatial data. LSCP leverages localized quantile regression to construct prediction intervals. Instead of i.i.d. assumptions, our theoretical analysis builds on weaker conditions of stationarity and spatial mixing, which is natural for spatial data, providing finite-sample bounds on the conditional coverage gap and establishing asymptotic guarantees for conditional coverage. We present experiments on both synthetic and real-world datasets to demonstrate that LSCP achieves accurate coverage with significantly tighter and more consistent prediction intervals across the spatial domain compared to existing methods.
Deep learning models for pulmonary disease screening from Computed Tomography (CT) scans promise to alleviate the immense workload on radiologists. Still, their high computational cost, stemming from processing entire 3D volumes, remains a major barrier to widespread clinical adoption. Current sub-sampling techniques often compromise diagnostic integrity by introducing artifacts or discarding critical information. To overcome these limitations, we propose an Efficient and Reliable Framework (ERF) that fundamentally improves the practicality of automated CT analysis. Our framework introduces two core innovations: (1) A Cluster-based Sub-Sampling (CSS) method that efficiently selects a compact yet comprehensive subset of CT slices by optimizing for both representativeness and diversity. By integrating an efficient k-Nearest Neighbor (k-NN) search with an iterative refinement process, CSS bypasses the computational bottlenecks of previous methods while preserving vital diagnostic features. (2) A lightweight Hybrid Uncertainty Quantification (HUQ) mechanism, which uniquely assesses both Aleatoric Uncertainty (AU) and Epistemic Uncertainty (EU) with minimal computational overhead. By maximizing the discrepancy between auxiliary classifiers, HUQ provides a robust reliability score, which is crucial for building trust in automated systems operating on partial data. Validated on two public datasets with 2,654 CT volumes across diagnostic tasks for 3 pulmonary diseases, our proposed ERF achieves diagnostic performance comparable to the full-volume analysis (over 90% accuracy and recall) while reducing processing time by more than 60%. This work represents a significant step towards deploying fast, accurate, and trustworthy AI-powered screening tools in time-sensitive clinical settings.
This paper introduces a novel approach to quantify the uncertainties in fault diagnosis of motor drives using Bayesian neural networks (BNN). Conventional data-driven approaches used for fault diagnosis often rely on point-estimate neural networks, which merely provide deterministic outputs and fail to capture the uncertainty associated with the inference process. In contrast, BNNs offer a principled framework to model uncertainty by treating network weights as probability distributions rather than fixed values. It offers several advantages: (a) improved robustness to noisy data, (b) enhanced interpretability of model predictions, and (c) the ability to quantify uncertainty in the decision-making processes. To test the robustness of the proposed BNN, it has been tested under a conservative dataset of gear fault data from an experimental prototype of three fault types at first, and is then incrementally trained on new fault classes and datasets to explore its uncertainty quantification features and model interpretability under noisy data and unseen fault scenarios.
Conformal prediction is widely adopted in uncertainty quantification, due to its post-hoc, distribution-free, and model-agnostic properties. In the realm of modern deep learning, researchers have proposed Feature Conformal Prediction (FCP), which deploys conformal prediction in a feature space, yielding reduced band lengths. However, the practical utility of FCP is limited due to the time-consuming non-linear operations required to transform confidence bands from feature space to output space. In this paper, we introduce Fast Feature Conformal Prediction (FFCP), which features a novel non-conformity score and is convenient for practical applications. FFCP serves as a fast version of FCP, in that it equivalently employs a Taylor expansion to approximate the aforementioned non-linear operations in FCP. Empirical validations showcase that FFCP performs comparably with FCP (both outperforming the vanilla version) while achieving a significant reduction in computational time by approximately 50x. The code is available at https://github.com/ElvisWang1111/FastFeatureCP
DEtection TRansformer (DETR) has emerged as a promising architecture for object detection, offering an end-to-end prediction pipeline. In practice, however, DETR generates hundreds of predictions that far outnumber the actual number of objects present in an image. This raises the question: can we trust and use all of these predictions? Addressing this concern, we present empirical evidence highlighting how different predictions within the same image play distinct roles, resulting in varying reliability levels across those predictions. More specifically, while multiple predictions are often made for a single object, our findings show that most often one such prediction is well-calibrated, and the others are poorly calibrated. Based on these insights, we demonstrate identifying a reliable subset of DETR's predictions is crucial for accurately assessing the reliability of the model at both object and image levels. Building on this viewpoint, we first tackle the shortcomings of widely used performance and calibration metrics, such as average precision and various forms of expected calibration error. Specifically, they are inadequate for determining which subset of DETR's predictions should be trusted and utilized. In response, we present Object-level Calibration Error (OCE), which is capable of assessing the calibration quality both across different models and among various configurations within a specific model. As a final contribution, we introduce a post hoc Uncertainty Quantification (UQ) framework that predicts the accuracy of the model on a per-image basis. By contrasting the average confidence scores of positive (i.e., likely to be matched) and negative predictions determined by OCE, the framework assesses the reliability of the DETR model for each test image.
Flow cytometry measurements are widely used in diagnostics and medical decision making. Incomplete understanding of sources of measurement uncertainty can make it difficult to distinguish autofluorescence and background sources from signals of interest. Moreover, established methods for modeling uncertainty overlook the fact that the apparent distribution of measurements is a convolution of the inherent the population variability (e.g., associated with calibration beads or cells) and instrument induced-effects. Such issues make it difficult, for example, to identify signals from small objects such as extracellular vesicles. To overcome such limitations, we formulate an explicit probabilistic measurement model that accounts for volume and labeling variation, background signals and fluorescence shot noise. Using raw data from routine per-event calibration measurements, we use this model to separate the aforementioned sources of uncertainty and demonstrate how such information can be used to facilitate decision-making and instrument characterization.
Constructing valid confidence sets is a crucial task in statistical inference, yet traditional methods often face challenges when dealing with complex models or limited observed sample sizes. These challenges are frequently encountered in modern applications, such as Likelihood-Free Inference (LFI). In these settings, confidence sets may fail to maintain a confidence level close to the nominal value. In this paper, we introduce two novel methods, TRUST and TRUST++, for calibrating confidence sets to achieve distribution-free conditional coverage. These methods rely entirely on simulated data from the statistical model to perform calibration. Leveraging insights from conformal prediction techniques adapted to the statistical inference context, our methods ensure both finite-sample local coverage and asymptotic conditional coverage as the number of simulations increases, even if n is small. They effectively handle nuisance parameters and provide computationally efficient uncertainty quantification for the estimated confidence sets. This allows users to assess whether additional simulations are necessary for robust inference. Through theoretical analysis and experiments on models with both tractable and intractable likelihoods, we demonstrate that our methods outperform existing approaches, particularly in small-sample regimes. This work bridges the gap between conformal prediction and statistical inference, offering practical tools for constructing valid confidence sets in complex models.
The problem of incorporating information from observations received serially in time is widespread in the field of uncertainty quantification. Within a probabilistic framework, such problems can be addressed using standard filtering techniques. However, in many real-world problems, some (or all) of the uncertainty is epistemic, arising from a lack of knowledge, and is difficult to model probabilistically. This paper introduces a possibilistic ensemble Kalman filter designed for this setting and characterizes some of its properties. Using possibility theory to describe epistemic uncertainty is appealing from a philosophical perspective, and it is easy to justify certain heuristics often employed in standard ensemble Kalman filters as principled approaches to capturing uncertainty within it. The possibilistic approach motivates a robust mechanism for characterizing uncertainty which shows good performance with small sample sizes, and can outperform standard ensemble Kalman filters at given sample size, even when dealing with genuinely aleatoric uncertainty.
The goal of this paper is to demonstrate and address challenges related to all aspects of performing a complete uncertainty quantification analysis of a complicated physics-based simulation like a 2D slab burner direct numerical simulation (DNS). The UQ framework includes the development of data-driven surrogate models, propagation of parametric uncertainties to the fuel regression rate--the primary quantity of interest--and Bayesian calibration of the latent heat of sublimation and a chemical reaction temperature exponent using experimental data. Two surrogate models, a Gaussian Process (GP) and a Hierarchical Multiscale Surrogate (HMS) were constructed using an ensemble of 64 simulations generated via Latin Hypercube sampling. HMS is superior for prediction demonstrated by cross-validation and able to achieve an error < 15% when predicting multiscale boundary quantities just from a few far field inputs. Subsequent Bayesian calibration of chemical kinetics and fuel response parameters against experimental observations showed that the default values used in the DNS should be higher to better match measurements. This study highlights the importance of surrogate model selection and parameter calibration in quantifying uncertainty in predictions of fuel regression rates in complex combustion systems.
The reliable recovery and uncertainty quantification of a fixed effect function $\mu$ in a functional mixed model, for modelling population- and object-level variability in noisily observed functional data, is a notoriously challenging task: variations along the $x$ and $y$ axes are confounded with additive measurement error, and cannot in general be disentangled. The question then as to what properties of $\mu$ may be reliably recovered becomes important. We demonstrate that it is possible to recover the size-and-shape of a square-integrable $\mu$ under a Bayesian functional mixed model. The size-and-shape of $\mu$ is a geometric property invariant to a family of space-time unitary transformations, viewed as rotations of the Hilbert space, that jointly transform the $x$ and $y$ axes. A random object-level unitary transformation then captures size-and-shape \emph{preserving} deviations of $\mu$ from an individual function, while a random linear term and measurement error capture size-and-shape \emph{altering} deviations. The model is regularized by appropriate priors on the unitary transformations, posterior summaries of which may then be suitably interpreted as optimal data-driven rotations of a fixed orthonormal basis for the Hilbert space. Our numerical experiments demonstrate utility of the proposed model, and superiority over the current state-of-the-art.
Convolutional neural networks (CNNs) are extremely popular and effective for image classification tasks but tend to be overly confident in their predictions. Various works have sought to quantify uncertainty associated with these models, detect out-of-distribution (OOD) inputs, or identify anomalous regions in an image, but limited work has sought to develop a holistic approach that can accurately estimate perception model confidence across various sources of uncertainty. We develop a probabilistic and reconstruction-based competency estimation (PaRCE) method and compare it to existing approaches for uncertainty quantification and OOD detection. We find that our method can best distinguish between correctly classified, misclassified, and OOD samples with anomalous regions, as well as between samples with visual image modifications resulting in high, medium, and low prediction accuracy. We describe how to extend our approach for anomaly localization tasks and demonstrate the ability of our approach to distinguish between regions in an image that are familiar to the perception model from those that are unfamiliar. We find that our method generates interpretable scores that most reliably capture a holistic notion of perception model confidence.
White Matter Hyperintensities (WMH) are key neuroradiological markers of small vessel disease present in brain MRI. Assessment of WMH is important in research and clinics. However, WMH are challenging to segment due to their high variability in shape, location, size, poorly defined borders, and similar intensity profile to other pathologies (e.g stroke lesions) and artefacts (e.g head motion). In this work, we apply the most effective techniques for uncertainty quantification (UQ) in segmentation to the WMH segmentation task across multiple test-time data distributions. We find a combination of Stochastic Segmentation Networks with Deep Ensembles yields the highest Dice and lowest Absolute Volume Difference % (AVD) score on in-domain and out-of-distribution data. We demonstrate the downstream utility of UQ, proposing a novel method for classification of the clinical Fazekas score using spatial features extracted for WMH segmentation and UQ maps. We show that incorporating WMH uncertainty information improves Fazekas classification performance and calibration, with median class balanced accuracy for classification models with (UQ and spatial WMH features)/(spatial WMH features)/(WMH volume only) of 0.71/0.66/0.60 in the Deep WMH and 0.82/0.77/0.73 in the Periventricular WMH regions respectively. We demonstrate that stochastic UQ techniques with high sample diversity can improve the detection of poor quality segmentations. Finally, we qualitatively analyse the semantic information captured by UQ techniques and demonstrate that uncertainty can highlight areas where there is ambiguity between WMH and stroke lesions, while identifying clusters of small WMH in deep white matter unsegmented by the model.
This article introduces a novel methodology that integrates singular value decomposition (SVD) with a shallow linear neural network for forecasting high resolution fluid mechanics data. The method, termed LC-SVD-DLinear, combines a low-cost variant of singular value decomposition (LC-SVD) with the DLinear architecture, which decomposes the input features-specifically, the temporal coefficients-into trend and seasonality components, enabling a shallow neural network to capture the non-linear dynamics of the temporal data. This methodology uses under-resolved data, which can either be input directly into the hybrid model or downsampled from high resolution using two distinct techniques provided by the methodology. Working with under-resolved cases helps reduce the overall computational cost. Additionally, we present a variant of the method, LC-HOSVD-DLinear, which combines a low-cost version of the high-order singular value decomposition (LC-HOSVD) algorithm with the DLinear network, designed for high-order data. These approaches have been validated using two datasets: first, a numerical simulation of three-dimensional flow past a circular cylinder at $Re = 220$; and second, an experimental dataset of turbulent flow passing a circular cylinder at $Re = 2600$. The combination of these datasets demonstrates the robustness of the method. The forecasting and reconstruction results are evaluated through various error metrics, including uncertainty quantification. The work developed in this article will be included in the next release of ModelFLOWs-app
Gaussian processes (GPs) can provide a principled approach to uncertainty quantification with easy-to-interpret kernel hyperparameters, such as the lengthscale, which controls the correlation distance of function values. However, selecting an appropriate kernel can be challenging. Deep GPs avoid manual kernel engineering by successively parameterizing kernels with GP layers, allowing them to learn low-dimensional embeddings of the inputs that explain the output data. Following the architecture of deep neural networks, the most common deep GPs warp the input space layer-by-layer but lose all the interpretability of shallow GPs. An alternative construction is to successively parameterize the lengthscale of a kernel, improving the interpretability but ultimately giving away the notion of learning lower-dimensional embeddings. Unfortunately, both methods are susceptible to particular pathologies which may hinder fitting and limit their interpretability. This work proposes a novel synthesis of both previous approaches: Thin and Deep GP (TDGP). Each TDGP layer defines locally linear transformations of the original input data maintaining the concept of latent embeddings while also retaining the interpretation of lengthscales of a kernel. Moreover, unlike the prior solutions, TDGP induces non-pathological manifolds that admit learning lower-dimensional representations. We show with theoretical and experimental results that i) TDGP is, unlike previous models, tailored to specifically discover lower-dimensional manifolds in the input data, ii) TDGP behaves well when increasing the number of layers, and iii) TDGP performs well in standard benchmark datasets.