This paper examines how to calibrate ensemble members for better prediction accuracy.
problem Improper calibration of deep neural networks leads to unreliable probability estimates.
method Theoretical analysis and empirical evaluation on CIFAR-100 dataset.
result Well-calibrated ensemble members do not guarantee a well-calibrated ensemble prediction, but a well-calibrated ensemble prediction cannot exceed the average performance of its members.
Deep ensembles don't necessarily improve calibration in low data regimes.
problem Calibration issues in deep learning models, especially in low data regimes.
method Examination of data-augmentation, ensembling, and post-processing calibration methods.
result Standard ensembling techniques can lead to less calibrated models in low data regimes.
Ensemble models improve prediction calibration for mismatched distributions.
problem Calibration issues in deep neural networks with mismatched train and test distributions.
method Simple data augmentation and mixing techniques for ensemble models.
result Improves calibration and accuracy on CIFAR10 and CIFAR100 benchmarks.
Paper proposes ensemble distillation for well-calibrated structured prediction.
problem Well-calibrated predictions are hard to achieve in structured prediction.
method Ensemble distillation framework for structured prediction.
result Ensemble distillation produces well-calibrated models with similar performance and calibration benefits to ensembles.
JUCAL jointly calibrates aleatoric and epistemic uncertainties in classifier ensembles.
problem Misrepresentation of predictive uncertainty due to unbalanced aleatoric and epistemic uncertainties.
method Joint Uncertainty Calibration (JUCAL) that jointly calibrates two constants to weight and scale uncertainties.
result Significantly outperforms state-of-the-art calibration methods across various text classification tasks.
Combining ensembles and data augmentation harms model calibration.
problem Improving model calibration and robustness with ensembles and data augmentation leads to a trade-off.
method Combining ensemble averaging and data augmentation techniques.
result Combining ensembles and data augmentation can harm model calibration.
Calibrated ensembles improve both ID and OOD accuracy in distribution shift.
problem Desired balance between in-distribution and out-of-distribution accuracy.
method Ensemble standard and robust models, calibrating on ID data only.
result ID-calibrated ensembles outperform state-of-the-art methods on multiple datasets.
Proposes a new method for deep ensembles that improves accuracy and calibration.
problem Improving accuracy and calibration of deep ensembles.
method Estimates confusion matrices of ensemble members and weighs them according to their inferred performance.
result Empirically shows superiority of soft Dawid Skene over ensemble averaging.
Better boosting with bandits improves probability estimation in online learning.
problem Poor calibration of probability estimates from boosting ensembles in online learning.
method Use bandit optimization to decide between updating ensemble or calibrator parameters.
result Superior performance in probability estimation compared to uncalibrated and naively-calibrated online boosting.
Jointly tuning ensemble models improves performance and uncertainty calibration.
problem Improving both predictive performance and uncertainty calibration in deep ensembles.
method Investigated the impact of jointly tuning weight decay, temperature scaling, and early stopping.
result Jointly tuning ensemble models generally matches or improves performance, with significant variation across tasks.
The paper extends calibration to sets of probabilistic classifiers, finding many ensembles are poorly calibrated.
problem Evaluating the validity of epistemic uncertainty in sets of probabilistic classifiers.
method Proposed a novel nonparametric calibration test for sets of probabilistic classifiers.
result Ensembles of deep neural networks are often not well calibrated.
Ensemble Kalman methods improve climate model calibration from noisy observations.
problem Calibrating parameters in complex climate models from noisy data.
method Comparing ensemble Kalman methods for efficiency in climate model calibration.
result Ensemble Kalman methods are more efficient and robust for parameter learning in climate models.
Packed-Ensembles improve uncertainty estimation in constrained hardware.
problem Hardware limitations restrict the size of ensembles and network capacity, degrading performance.
method Packed-Ensembles (PE) design and train lightweight structured ensembles by modulating encoding space and parallelizing into a single backbone.
result PE accurately preserves diversity and maintains performance on key metrics like accuracy, calibration, and out-of-distribution detection.
Ensemble learning is a mainstay in modern data science practice. Conventional ensemble algorithms assigns to base models a set of deterministic, constant model weights that (1) do not fully account for variations in base model accuracy across subgroups, nor (2) provide uncertainty estimates for the ensemble prediction,…
Improved wind speed forecasts for power generation using machine learning.
problem Improving the accuracy and reliability of wind speed predictions for power generation.
method A novel machine learning approach for calibrating wind speed ensemble forecasts.
result The proposed method improves the calibration and accuracy of probabilistic and point forecasts.
PEP improves deep network performance and calibration by perturbing optimal parameters.
problem Improving deep network performance and calibration.
method Parameter Ensembling by Perturbation (PEP) constructs an ensemble of parameter values as random perturbations of the optimal set, maximizing log-likelihood on validation data.
result PEP provides a small to substantial improvement in calibration and log-likelihood, and in some cases, classification accuracy.
Proposes a three-stage debiasing framework to improve out-of-distribution accuracy.
problem Inaccurate uncertainty estimations in bias-only models damage ensemble-based debiasing performance.
method Calibrates the bias-only model to improve its uncertainty estimations, creating a three-stage ensemble-based debiasing framework.
result The three-stage debiasing framework consistently outperforms traditional methods in out-of-distribution accuracy.
This work evaluates uncertainty in deep Gaussian processes.
problem Uncertainty quantification in deep Gaussian processes.
method Hierarchical deep Gaussian processes (DGPs) and Deep Sigma Point Processes (DSPPs) evaluated on regression and classification tasks.
result DSPPs provide strong in-distribution calibration but are less robust under distribution shift compared to ensembles.
FoRDE uses input gradients to improve neural network ensembles.
problem Improving neural network ensembles for robustness and accuracy.
method Proposes FoRDE, an ensemble learning method based on ParVI, which repels function space by input gradients.
result FoRDE significantly outperforms DEs and other ensemble methods in accuracy and calibration.
Deep ensembles outperform deep ensembles of Bayesian neural networks on in-distribution data.
problem Improving model calibration and uncertainty quantification in Bayesian Neural Networks.
method Systematic investigation of deep ensembles of Bayesian Neural Networks across various datasets and architectures.
result Deep ensembles consistently outperform deep ensembles of Bayesian neural networks on in-distribution data.
Mix-n-Match improves uncertainty calibration in deep learning.
problem Post-hoc calibration of machine learning classifiers.
method Ensemble and composition strategies to improve accuracy, efficiency, and expressive power.
result Mix-n-Match strategies achieve better data-efficiency and expressive power while maintaining classification accuracy.
New method creates diverse neural ensembles for better uncertainty estimation and robustness.
problem Creating more robust neural networks for uncertainty estimation and dataset shift.
method Automatically constructing ensembles with varying architectures.
result Ensembles with varying architectures outperform deep ensembles in accuracy, uncertainty calibration, and robustness.
EnsLoss combines multiple loss functions to prevent overfitting in classification.
problem Preventing overfitting in classification models.
method EnsLoss is an ensemble method that combines loss functions, ensuring calibration and consistency.
result EnsLoss improves classification accuracy compared to fixed loss methods.
A test assesses the calibration of set-based epistemic uncertainty representations.
problem Evaluating the accuracy of set-based representations of epistemic uncertainty in machine learning.
method Proposes a novel statistical test to determine if a convex combination of predictions is calibrated, allowing instance-level variability.
result Demonstrates the benefits of capturing instance-level variability on synthetic and real-world experiments.
Simple mode exploration methods do not improve performance in neural networks.
problem Improving predictive probabilities in neural networks.
method Exploring local regions around diverse solutions using simple methods.
result Simple mode exploration methods do not improve performance.
The adaptation of numerical wind wave models to the local time-spatial conditions is a problem that can be solved by using various calibration techniques. However, the obtained sets of physical parameters become over-tuned to specific events if there is a lack of observations. In this paper, we propose a robust evoluti…
Study on learning to defer to multiple experts with consistent surrogates and confidence calibration.
problem Addressing the open problems of consistent surrogates, confidence calibration, and ensembling of experts.
method Derive two consistent surrogates (softmax and OvA) and propose a conformal inference technique for choosing experts.
result The OvA-based loss does not cause mis-calibration propagation, while the softmax-based loss does.
This work investigates power laws in deep neural network ensembles and predicts their performance.
problem Understanding the performance of deep neural network ensembles and their optimal structure.
method Investigated the behavior of negative log-likelihood (CNLL) of a deep ensemble as a function of ensemble size and member network size, identifying power law dependencies.
result One large network may perform worse than an ensemble of several medium-size networks, known as a memory split.
Neural networks learn from ensemble forecasts without considering their order.
problem Improving reliability of probabilistic weather forecasts.
method Permutation-invariant neural networks for postprocessing ensemble forecasts.
result Models achieve state-of-the-art prediction quality in surface temperature and wind gust forecasts.
Improves model calibration by addressing adversarially unrobust inputs.
problem Miscalibrated predictions and lack of adversarial robustness in neural networks.
method AR-AdaLS, an adaptive label smoothing method that considers adversarial robustness.
result AR-AdaLS improves model calibration, even under distributional shifts.
The paper presents a method for generating well-calibrated prediction intervals using quality-driven deep ensembles.
problem Generating reliable prediction intervals for regression analysis.
method A multi-objective loss function combining quality measures for prediction intervals and point estimates, with a penalty function to ensure semantic integrity and stability.
result The method produces well-calibrated prediction intervals and point estimates, capturing both aleatoric and epistemic uncertainty.
Efficiently builds diverse sub-model ensembles for robust self-supervised learning.
problem Challenges in diversity and efficiency of deep ensembles for self-supervised representation learning.
method Ensemble of independent sub-networks with a new loss function for diversity.
result Significantly improves prediction reliability and model calibration.
New algorithm reduces overfitting in neural networks.
problem Overfitting in neural networks.
method Integrates SMC with SGHMC for mini-batch sampling.
result SMCSGHMC outperforms SGD and deep ensembles.
New method calibrates uncertainty in molecular property predictions.
problem Uncalibrated uncertainty estimates in molecular property predictions.
method Message Passing Neural Networks with calibrated probabilistic predictive distribution.
result Accurate molecular formation energy predictions with well-calibrated uncertainty.
Learning accurate probabilistic models from data is crucial in many practical tasks in data mining. In this paper we present a new non-parametric calibration method called \textit{ensemble of near isotonic regression} (ENIR). The method can be considered as an extension of BBQ, a recently proposed calibration method, a…
Method provides formal guarantees for decomposing model uncertainty.
problem Decomposing model uncertainty into aleatoric and epistemic components.
method Higher-order calibration using k-snapshots.
result Formal guarantees for aleatoric uncertainty matching real-world distribution.
Multi-headed ensembles boost model performance with faster training.
problem Limited computational resources hinder ensemble search performance.
method Extend NES to multi-headed ensembles, leveraging end-to-end training and one-shot NAS methods.
result Multi-headed ensemble search finds robust ensembles 3 times faster with comparable performance.
This work reviews and evaluates methods for predicting prediction intervals in regression problems.
problem Calibration of prediction intervals in regression problems.
method Four classes of methods: Bayesian, ensemble, direct interval estimation, and conformal prediction.
result Conformal prediction can be used as a general calibration procedure.
Reduces false positives in classifying rare online platforms.
problem Challenges in accurately identifying rare online platforms with ML.
method Calibrated probabilities and ensembles to reduce bias.
result Significantly reduces false positives in rare event detection.
CLEAR calibrates both aleatoric and epistemic uncertainties for better predictive intervals.
problem Balanced uncertainty quantification for reliable predictive modeling.
method CLEAR uses two parameters, γ1 and γ2, to combine aleatoric and epistemic uncertainties.
result Clear achieves significant improvements in interval width and coverage.
Bayesian Quadrature improves ensembling for neural networks with dispersed likelihood peaks.
problem Ensembling neural networks struggles with dispersed, narrow peaks in likelihood surfaces.
method Uses Bayesian Quadrature to construct weighted ensembles of architectures.
result Empirically outperforms state-of-the-art baselines in test likelihood, accuracy, and expected calibration error.
A new method predicts precipitation distributions from ensemble forecasts.
problem Improving accuracy and calibration of precipitation forecasts.
method Distributional regression U-Nets for postprocessing ensemble precipitation forecasts.
result Competitive performance in continuous ranked probability score, especially for heavy precipitation.
Transforms ensemble predictions to maintain interpretability.
problem Loss of interpretability in deep ensembles.
method Proposes transformation ensembles that aggregate predictions while preserving interpretability.
result Transformation ensembles yield better predictions than individual models and maintain interpretability.
Regression Prior Networks improve ensemble performance on regression tasks.
problem Improving ensemble performance on regression tasks.
method Extending Prior Networks and Ensemble Distribution Distillation (EnD2) to regression tasks using the Normal-Wishart distribution. result Regression Prior Networks yield performance competitive with ensemble approaches on regression tasks.
Framework for precise recall control in spatial conflation tasks.
problem Precise recall control in large-scale spatial conflation tasks to avoid downstream analytics failures and excessive manual review.
method End-to-end framework using equigrid bounding-box filter, CSR representation, neural ranker, and inverse-variance weighted ensemble of threshold estimators.
result Achieves exact recall with sub-percent variance over tens of millions of geometry pairs, runs on a single TPU v3 core.
Machine learning improves cloud cover forecasting.
problem Improving accuracy of total cloud cover predictions.
method Investigated multilayer perceptron, gradient boosting machines, random forest, logistic regression models.
result RF models provide the smallest increase in predictive performance, while MLP, POLR, and GBM approaches perform best.
New hyperparameter ensembles boost neural network performance and uncertainty.
problem Improving neural network robustness and uncertainty quantification.
method Designing ensembles over both weights and hyperparameters, stratified across random initializations.
result Hyper-deep and hyper-batch ensembles outperform deep and batch ensembles on various architectures.
TOO optimizes stochastic epidemiological models by finding both parameter settings and random seeds.
problem Calibrating stochastic epidemiological models to match empirical observations.
method Gaussian process surrogates and Thompson sampling for optimization.
result Produces actual trajectories consistent with ground truth.