Uncertainty quantification enables users to assess the reliability of responses generated by large language models (LLMs). We present a novel Question Rephrasing technique to evaluate the input uncertainty of LLMs, which refers to the uncertainty arising from equivalent variations of the inputs provided to LLMs. This technique is integrated with sampling methods that measure the output uncertainty of LLMs, thereby offering a more comprehensive uncertainty assessment. We validated our approach on property prediction and reaction prediction for molecular chemistry tasks.
We present a new approach for nonlinear dimensionality reduction, specifically designed for computationally expensive mathematical models. We leverage autoencoders to discover a one-dimensional neural active manifold (NeurAM) capturing the model output variability, plus a simultaneously learnt surrogate model with inputs on this manifold. The proposed dimensionality reduction framework can then be applied to perform outer loop many-query tasks, like sensitivity analysis and uncertainty propagation. In particular, we prove, both theoretically under idealized conditions, and numerically in challenging test cases, how NeurAM can be used to obtain multifidelity sampling estimators with reduced variance by sampling the models on the discovered low-dimensional and shared manifold among models. Several numerical examples illustrate the main features of the proposed dimensionality reduction strategy, and highlight its advantages with respect to existing approaches in the literature.
Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models. However, the use of Gaussian priors for last layer weights in Bayesian Last Layer (BLL) models limits their expressive capacity when faced with non-Gaussian, outlier-rich, or high-dimensional datasets. To address this shortfall, we introduce a novel approach that combines diffusion techniques and implicit priors for variational learning of Bayesian last layer weights. This method leverages implicit distributions for modeling weight priors in BLL, coupled with diffusion samplers for approximating true posterior predictions, thereby establishing a comprehensive Bayesian prior and posterior estimation strategy. By delivering an explicit and computationally efficient variational lower bound, our method aims to augment the expressive abilities of BLL models, enhancing model accuracy, calibration, and out-of-distribution detection proficiency. Through detailed exploration and experimental validation, We showcase the method's potential for improving predictive accuracy and uncertainty quantification while ensuring computational efficiency.
We consider the problem of data-driven stochastic optimal control of an unknown LTI dynamical system. Assuming the process noise is normally distributed, we pose the problem of steering the state's mean and covariance to a target normal distribution, under noisy data collected from the underlying system, a problem commonly referred to as covariance steering (CS). A novel framework for Data-driven Uncertainty quantification and density STeering (DUST) is presented that simultaneously characterizes the noise affecting the measured data and designs an optimal affine-feedback controller to steer the density of the state to a prescribed terminal value. We use both indirect and direct data-driven design approaches based on the notions of persistency of excitation and subspace predictors to exactly represent the mean and covariance dynamics of the state in terms of the data and noise realizations. Since both the mean and the covariance steering sub-problems are plagued with distributional uncertainty arising from noisy data collection, we first estimate the noise realization from this dataset and subsequently compute tractable upper bounds on the estimation errors. The moment steering problems are then solved to optimality using techniques from robust control and robust optimization. Lastly, we present an alternative control design approach based on the certainty equivalence principle and interpret the problem as one of CS under multiplicative uncertainties. We analyze the performance and efficacy of each of these data-driven approaches using a case study and compare them with their model-based counterparts.
One of the most promising solutions for uncertainty quantification in high-dimensional statistics is the debiased LASSO that relies on unconstrained $\ell_1$-minimization. The initial works focused on real Gaussian designs as a toy model for this problem. However, in medical imaging applications, such as compressive sensing for MRI, the measurement system is represented by a (subsampled) complex Fourier matrix. The purpose of this work is to extend the method to the MRI case in order to construct confidence intervals for each pixel of an MR image. We show that a sufficient amount of data is $n \gtrsim \max\{ s_0\log^2 s_0\log p, s_0 \log^2 p \}$.
Intelligent agents must be able to articulate its own uncertainty. In this work, we show that pre-trained sequence models are naturally capable of probabilistic reasoning over exchangeable data points -- forming informed beliefs and sharpening them as it gathers more information. A sequence model learns the relationship between observations, which differs from typical Bayesian models that quantify uncertainty over latent parameters through priors and likelihoods (e.g., topic models). Despite the apparent difference, we illustrate how exchangeable sequence modeling provides a valid Bayesian model by going back to De Finetti's classical predictive view of probabilistic reasoning: uncertainty comes from data that has not been observed yet, rather than latent parameters. From this perspective, pre-training autoregressive models is equivalent to formulating informed beliefs based on prior observations ("empirical Bayes"), and forward generation is equivalent to simulating instantiations of an environment ("posterior inference"). In particular, exchangeable sequence models can explicitly perform statistical inference; epistemic uncertainty over latent environments is captured by variation in predicted future observations. Formally, we show the sequence prediction loss controls the quality of uncertainty quantification, and propose several approaches for encoding exchangeability in sequence model architectures: data augmentation, regularization, and causal masking.
In Part I, we created an ensemble based on Spherical Fourier Neural Operators. As initial condition perturbations, we used bred vectors, and as model perturbations, we used multiple checkpoints trained independently from scratch. Based on diagnostics that assess the ensemble's physical fidelity, our ensemble has comparable performance to operational weather forecasting systems. However, it requires orders of magnitude fewer computational resources. Here in Part II, we generate a huge ensemble (HENS), with 7,424 members initialized each day of summer 2023. We enumerate the technical requirements for running huge ensembles at this scale. HENS precisely samples the tails of the forecast distribution and presents a detailed sampling of internal variability. HENS has two primary applications: (1) as a large dataset with which to study the statistics and drivers of extreme weather and (2) as a weather forecasting system. For extreme climate statistics, HENS samples events 4$\sigma$ away from the ensemble mean. At each grid cell, HENS increases the skill of the most accurate ensemble member and enhances coverage of possible future trajectories. As a weather forecasting model, HENS issues extreme weather forecasts with better uncertainty quantification. It also reduces the probability of outlier events, in which the verification value lies outside the ensemble forecast distribution.
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 incorporating Bayesian neural networks as the building blocks for the branch and trunk networks, our framework endows DeepONet with uncertainty quantification. The use of R\'enyi's $\alpha$-divergence, instead of the Kullback-Leibler divergence (KLD), commonly used in standard variational inference, mitigates issues related to prior misspecification that are prevalent in Variational Bayesian DeepONets. This approach offers enhanced flexibility and robustness. We demonstrate that modifying the variational objective function yields superior results in terms of minimising the mean squared error and improving the negative log-likelihood on the test set. Our framework's efficacy is validated across various mechanical systems, where it outperforms both deterministic and standard KLD-based VI DeepONets in predictive accuracy and uncertainty quantification. The hyperparameter $\alpha$, which controls the degree of robustness, can be tuned to optimise performance for specific problems. We apply this approach to a range of mechanics problems, including gravity pendulum, advection-diffusion, and diffusion-reaction systems. Our findings underscore the potential of $\alpha$-VI DeepONet to advance the field of data-driven operator learning and its applications in engineering and scientific domains.
While large language models are rapidly moving towards consumer-facing applications, they are often still prone to factual errors and hallucinations. In order to reduce the potential harms that may come from these errors, it is important for users to know to what extent they can trust an LLM when it makes a factual claim. To this end, we study the problem of uncertainty quantification of factual correctness in long-form natural language generation. Given some output from a large language model, we study both uncertainty at the level of individual claims contained within the output (via calibration) and uncertainty across the entire output itself (via conformal prediction). Moreover, we invoke multicalibration and multivalid conformal prediction to ensure that such uncertainty guarantees are valid both marginally and across distinct groups of prompts. Using the task of biography generation, we demonstrate empirically that having access to and making use of additional group attributes for each prompt improves both overall and group-wise performance. As the problems of calibration, conformal prediction, and their multi-group counterparts have not been extensively explored previously in the context of long-form text generation, we consider these empirical results to form a benchmark for this setting.
Process-based hydrologic models are invaluable tools for understanding the terrestrial water cycle and addressing modern water resources problems. However, many hydrologic models are computationally expensive and, depending on the resolution and scale, simulations can take on the order of hours to days to complete. While techniques such as uncertainty quantification and optimization have become valuable tools for supporting management decisions, these analyses typically require hundreds of model simulations, which are too computationally expensive to perform with a process-based hydrologic model. To address this gap, we assess a hybrid modeling workflow in which a process-based model is used to generate an initial set of simulations and a machine learning (ML) surrogate model is then trained to perform the remaining simulations required for downstream analysis. As a case study, we apply this workflow to simulations of variably saturated groundwater flow at a prospective managed aquifer recharge site. We compare the accuracy and computational efficiency of several ML architectures, including deep convolutional networks, recurrent neural networks, vision transformers, and networks with Fourier transforms. Our results demonstrate that ML surrogate models can achieve under 10% mean absolute percentage error and yield order-of-magnitude runtime savings over process-based models. Building on these findings, we examine the impacts of key modeling choices on surrogate model accuracy and efficiency. Results show that a normalized loss function improves training stability, while min-max data normalization can significantly reduce error up to a factor of 10 when compared to other treatments such as Z-score and no normalization. Downsampling input features using an autoencoder also decreases memory requirements by training with tensors 4% their original size. By reducing computational costs and...
As data plays an increasingly pivotal role in decision-making, the emergence of data markets underscores the growing importance of data valuation. Within the machine learning landscape, Data Shapley stands out as a widely embraced method for data valuation. However, a limitation of Data Shapley is its assumption of a fixed dataset, contrasting with the dynamic nature of real-world applications where data constantly evolves and expands. This paper establishes the relationship between Data Shapley and infinite-order U-statistics and addresses this limitation by quantifying the uncertainty of Data Shapley with changes in data distribution from the perspective of U-statistics. We make statistical inferences on data valuation to obtain confidence intervals for the estimations. We construct two different algorithms to estimate this uncertainty and provide recommendations for their applicable situations. We also conduct a series of experiments on various datasets to verify asymptotic normality and propose a practical trading scenario enabled by this method.
We consider the problem of Bayesian regression with trustworthy uncertainty quantification. We define that the uncertainty quantification is trustworthy if the ground truth can be captured by intervals dependent on the predictive distributions with a pre-specified probability. Furthermore, we propose, Trust-Bayes, a novel optimization framework for Bayesian meta learning which is cognizant of trustworthy uncertainty quantification without explicit assumptions on the prior model/distribution of the functions. We characterize the lower bounds of the probabilities of the ground truth being captured by the specified intervals and analyze the sample complexity with respect to the feasible probability for trustworthy uncertainty quantification. Monte Carlo simulation of a case study using Gaussian process regression is conducted for verification and comparison with the Meta-prior algorithm.
Predicting chaotic dynamical systems is critical in many scientific fields, such as weather forecasting, but challenging due to the characteristic sensitive dependence on initial conditions. Traditional modeling approaches require extensive domain knowledge, often leading to a shift towards data-driven methods using machine learning. However, existing research provides inconclusive results on which machine learning methods are best suited for predicting chaotic systems. In this paper, we compare different lightweight and heavyweight machine learning architectures using extensive existing benchmark databases, as well as a newly introduced database that allows for uncertainty quantification in the benchmark results. In addition to state-of-the-art methods from the literature, we also present new advantageous variants of established methods. Hyperparameter tuning is adjusted based on computational cost, with more tuning allocated to less costly methods. Furthermore, we introduce the cumulative maximum error, a novel metric that combines desirable properties of traditional metrics and is tailored for chaotic systems. Our results show that well-tuned simple methods, as well as untuned baseline methods, often outperform state-of-the-art deep learning models, but their performance can vary significantly with different experimental setups. These findings highlight the importance of aligning prediction methods with data characteristics and caution against the indiscriminate use of overly complex models.
Volumetry is one of the principal downstream applications of 3D medical image segmentation, for example, to detect abnormal tissue growth or for surgery planning. Conformal Prediction is a promising framework for uncertainty quantification, providing calibrated predictive intervals associated with automatic volume measurements. However, this methodology is based on the hypothesis that calibration and test samples are exchangeable, an assumption that is in practice often violated in medical image applications. A weighted formulation of Conformal Prediction can be framed to mitigate this issue, but its empirical investigation in the medical domain is still lacking. A potential reason is that it relies on the estimation of the density ratio between the calibration and test distributions, which is likely to be intractable in scenarios involving high-dimensional data. To circumvent this, we propose an efficient approach for density ratio estimation relying on the compressed latent representations generated by the segmentation model. Our experiments demonstrate the efficiency of our approach to reduce the coverage error in the presence of covariate shifts, in both synthetic and real-world settings. Our implementation is available at https://github.com/benolmbrt/wcp_miccai
Investigating the genetic architecture of complex diseases is challenging due to the multifactorial and interactive landscape of genomic and environmental influences. Although genome-wide association studies (GWAS) have identified thousands of variants for multiple complex traits, conventional statistical approaches can be limited by simplified assumptions such as linearity and lack of epistasis in models. In this work, we trained artificial neural networks to predict complex traits using both simulated and real genotype-phenotype datasets. We extracted feature importance scores via different post hoc interpretability methods to identify potentially associated loci (PAL) for the target phenotype and devised an approach for obtaining p-values for the detected PAL. Simulations with various parameters demonstrated that associated loci can be detected with good precision using strict selection criteria. By applying our approach to the schizophrenia cohort in the Estonian Biobank, we detected multiple loci associated with this highly polygenic and heritable disorder. There was significant concordance between PAL and loci previously associated with schizophrenia and bipolar disorder, with enrichment analyses of genes within the identified PAL predominantly highlighting terms related to brain morphology and function. With advancements in model optimization and uncertainty quantification, artificial neural networks have the potential to enhance the identification of genomic loci associated with complex diseases, offering a more comprehensive approach for GWAS and serving as initial screening tools for subsequent functional studies.
This study introduces novel superior scoring rules called Penalized Brier Score (PBS) and Penalized Logarithmic Loss (PLL) to improve model evaluation for probabilistic classification. Traditional scoring rules like Brier Score and Logarithmic Loss sometimes assign better scores to misclassifications in comparison with correct classifications. This discrepancy from the actual preference for rewarding correct classifications can lead to suboptimal model selection. By integrating penalties for misclassifications, PBS and PLL modify traditional proper scoring rules to consistently assign better scores to correct predictions. Formal proofs demonstrate that PBS and PLL satisfy strictly proper scoring rule properties while also preferentially rewarding accurate classifications. Experiments showcase the benefits of using PBS and PLL for model selection, model checkpointing, and early stopping. PBS exhibits a higher negative correlation with the F1 score compared to the Brier Score during training. Thus, PBS more effectively identifies optimal checkpoints and early stopping points, leading to improved F1 scores. Comparative analysis verifies models selected by PBS and PLL achieve superior F1 scores. Therefore, PBS and PLL address the gap between uncertainty quantification and accuracy maximization by encapsulating both proper scoring principles and explicit preference for true classifications. The proposed metrics can enhance model evaluation and selection for reliable probabilistic classification.
Sepsis is the leading cause of in-hospital mortality in the USA. Early sepsis onset prediction and diagnosis could significantly improve the survival of sepsis patients. Existing predictive models are usually trained on high-quality data with few missing information, while missing values widely exist in real-world clinical scenarios (especially in the first hours of admissions to the hospital), which causes a significant decrease in accuracy and an increase in uncertainty for the predictive models. The common method to handle missing values is imputation, which replaces the unavailable variables with estimates from the observed data. The uncertainty of imputation results can be propagated to the sepsis prediction outputs, which have not been studied in existing works on either sepsis prediction or uncertainty quantification. In this study, we first define such propagated uncertainty as the variance of prediction output and then introduce uncertainty propagation methods to quantify the propagated uncertainty. Moreover, for the potential high-risk patients with low confidence due to limited observations, we propose a robust active sensing algorithm to increase confidence by actively recommending clinicians to observe the most informative variables. We validate the proposed models in both publicly available data (i.e., MIMIC-III and AmsterdamUMCdb) and proprietary data in The Ohio State University Wexner Medical Center (OSUWMC). The experimental results show that the propagated uncertainty is dominant at the beginning of admissions to hospitals and the proposed algorithm outperforms state-of-the-art active sensing methods. Finally, we implement a SepsisLab system for early sepsis prediction and active sensing based on our pre-trained models. Clinicians and potential sepsis patients can benefit from the system in early prediction and diagnosis of sepsis.
Areas of computational mechanics such as uncertainty quantification and optimization usually involve repeated evaluation of numerical models that represent the behavior of engineering systems. In the case of complex nonlinear systems however, these models tend to be expensive to evaluate, making surrogate models quite valuable. Artificial neural networks approximate systems very well by taking advantage of the inherent information of its given training data. In this context, this paper investigates the improvement of the training process by including sensitivity information, which are partial derivatives w.r.t. inputs, as outlined by Sobolev training. In computational mechanics, sensitivities can be applied to neural networks by expanding the training loss function with additional loss terms, thereby improving training convergence resulting in lower generalisation error. This improvement is shown in two examples of linear and non-linear material behavior. More specifically, the Sobolev designed loss function is expanded with residual weights adjusting the effect of each loss on the training step. Residual weighting is the given scaling to the different training data, which in this case are response and sensitivities. These residual weights are optimized by an adaptive scheme, whereby varying objective functions are explored, with some showing improvements in accuracy and precision of the general training convergence.
User identification through smartphones and wearable sensors holds promise but faces challenges from variability in user activities and sampling windows. This paper presents a method that takes into account uncertainties to enhance the performance of user identification. The conventional sliding window technique is commonly employed for segmenting data, but using small windows can decrease classification performance by creating similar instances with different labels. Conversely, larger windows introduce concept drift resulting from mixed activity patterns. To tackle these challenges, the proposed method assesses the prediction uncertainty of a CNN classifier trained on small window sizes using the Monte Carlo Dropout technique and combines the predictions within a decision window. Uncertainty scores assist in discounting uncertain predictions during the final decision-making. Through experiments on five real-world datasets, the study demonstrates improved performance in identifying users across a range of activities compared to existing methods. It was also directly compared to state-of-the-art methods using two well-known datasets, improving accuracy by 1.29% in one case and 7.98% in the other. These findings validate the effectiveness of the new approach for continuous user identification, even when faced with unpredictable user behavior.
Colorectal polyps are generally benign alterations that, if not identified promptly and managed successfully, can progress to cancer and cause affectations on the colon mucosa, known as adenocarcinoma. Today advances in Deep Learning have demonstrated the ability to achieve significant performance in image classification and detection in medical diagnosis applications. Nevertheless, these models are prone to overfitting, and making decisions based only on point estimations may provide incorrect predictions. Thus, to obtain a more informed decision, we must consider point estimations along with their reliable uncertainty quantification. In this paper, we built different Bayesian neural network approaches based on the flexibility of posterior distribution to develop semantic segmentation of colorectal polyp images. We found that these models not only provide state-of-the-art performance on the segmentation of this medical dataset but also, yield accurate uncertainty estimates. We applied multiplicative normalized flows(MNF) and reparameterization trick on the UNET, FPN, and LINKNET architectures tested with multiple backbones in deterministic and Bayesian versions. We report that the FPN + EfficientnetB7 architecture with MNF is the most promising option given its IOU of 0.94 and Expected Calibration Error (ECE) of 0.004, combined with its superiority in identifying difficult-to-detect colorectal polyps, which is effective in clinical areas where early detection prevents the development of colon cancer.