The paper highlights how machine learning calibrations can be biased by training data.
problem Machine learning calibrations can be biased by the training data, affecting downstream analyses.
method The paper examines simulation-based and data-based calibrations, highlighting their prior dependence and proposing solutions.
result A recently proposed Gaussian Ansatz approach can avoid some biases in simulation-based calibrations.
Bayesian neural networks improve uncertainty calibration with DAP priors.
problem Improving predictive uncertainty in deep learning models outside training data.
method Distance-Aware Prior (DAP) calibration method to correct overconfidence.
result Demonstrated effectiveness in various classification and regression tasks.
Blade uses diffusion priors to accurately and calibratedly infer complex systems.
problem Derivative-free Bayesian inversion for high-dimensional, nonlinear problems with costly forward models.
method Blade employs an ensemble of interacting particles and diffusion models as priors, querying forward models only through evaluations.
result Blade produces well-calibrated posterior samples that existing methods cannot, improving with more iterations and particles.
PRCD-MAP learns to trust imperfect priors in causal discovery, improving accuracy and robustness.
problem Tackles the brittle trade-off between blind trust and rejection of external priors in causal discovery.
method Proposes PRCD-MAP, a soft prior-consumption layer that assigns per-edge trust to imperfect priors and modulates regularization in a MAP objective.
result Enjoys a population-level safety guarantee and outperforms existing methods on real-world causal discovery tasks.
FMP sampling improves model calibration without sharing data.
problem Difficulties in specifying priors for modern neural networks.
method FMP sampling replaces prior and likelihood with a predictive distribution, running the sampler centrally.
result FMP sampling significantly improves calibration over baseline methods.
This paper improves multi-class calibration methods using mutual information maximization-based binning.
problem Calibration of deep neural network predictions, especially for small prior classes.
method I-Max concept for binning, shared class-wise calibration strategy.
result Improves multi-class ranking and calibration performance using a small calibration set.
Machine learning models deployed in real-world applications are often evaluated with precision-based metrics such as F1-score or AUC-PR (Area Under the Curve of Precision Recall). Heavily dependent on the class prior, such metrics make it difficult to interpret the variation of a model's performance over different subp…
Bayesian framework calibrates imperfect models using physics-informed priors and Hamiltonian Monte Carlo.
problem Quantifying uncertainty in imperfect computer models described by differential equations.
method Physics-informed Gaussian process priors, discrepancy function, Hamiltonian Monte Carlo, data approximations.
result Framework accurately recovers true parameters and produces accurate predictions.
Better uncertainty estimates for neural networks using Gaussian process priors.
problem Poor uncertainty estimates in neural networks, especially on out-of-distribution data.
method Characterize the function-space prior of an ensemble of infinitely-wide neural networks as a Gaussian process and use it to build a probabilistic model.
result The approach improves calibration of neural networks, especially under distributional shift.
Generative model learns functional vector fields for pharmacokinetics.
problem Generating accurate virtual cohorts and forecasting patient trajectories without manual tuning.
method Prior-Fitted Functional Flows model, learning functional vector fields conditioned on sparse, irregular data.
result State-of-the-art predictive accuracy on real-world datasets.
Develops a new algorithm to calibrate signed datasets to specified marginals.
problem Calibrating signed datasets to specified marginals.
method Extends Schrödinger-Fortet-Sinkhorn paradigm to sign-indefinite multi-dimensional arrays.
result Proposes an optimization problem to update a sign-indefinite prior to match given marginals.
Prior-weighted logistic regression has become a standard tool for calibration in speaker recognition. Logistic regression is the optimization of the expected value of the logarithmic scoring rule. We generalize this via a parametric family of proper scoring rules. Our theoretical analysis shows how different members of…
New method improves calibration of BayesCG for better uncertainty quantification.
problem Bayesian conjugate gradient method's poor calibration limits its utility.
method Randomized postiteration strategy to enhance posterior calibration.
result The method improves the distribution of posterior errors and enhances uncertainty quantification.
New calibration measure SSCE ensures truthful prediction, unlike existing measures.
problem Ensuring truthful calibration measures in sequential prediction.
method Introduced a new calibration measure, Subsampled Smooth Calibration Error (SSCE).
result SSCE ensures truthful prediction, while existing measures are far from truthful.
Midicoth compresses online probability estimates by correcting prior smoothing biases.
problem Compression inefficiency due to prior smoothing in adaptive models.
method Micro-diffusion denoising applied in a bitwise tree hierarchy.
result Significant compression improvement with reliable calibration.
We show how to compute the Bayes error-rate for speaker verifiers.
problem How many errors does a speaker verifier make in a hundred trials?
method We compute the Bayes error-rate using calibrated likelihood ratios and user-supplied prior probabilities.
result The Bayes error-rate is upper bounded by the minimum of EER, P, and 1-P.
Label shift refers to the phenomenon where the prior class probability p(y) changes between the training and test distributions, while the conditional probability p(x|y) stays fixed. Label shift arises in settings like medical diagnosis, where a classifier trained to predict disease given symptoms must be adapted to sc…
New method calibrates neural network uncertainty for medical images.
problem Uncalibrated probabilistic outputs from deep neural networks in medical diagnosis.
method Functional space variational inference for Bayesian neural networks.
result Better calibrated uncertainty estimates at lower computational cost.
Improved DNN calibration without sacrificing accuracy.
problem Poor calibration of over-parametrized DNNs in safety-critical applications.
method Decoupling feature extraction and classification layers, and applying Gaussian priors.
result Significant improvement in model calibration with minimal training cost.
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.
Unified detector calibration and simulation using MLE from generative models.
problem Combining detector calibration and simulation using traditional methods.
method Maximum likelihood estimation from conditional generative models.
result Prior-independent and non-Gaussian resolutions possible.
We study statistical calibration, i.e., adjusting features of a computational model that are not observable or controllable in its associated physical system. We focus on functional calibration, which arises in many manufacturing processes where the unobservable features, called calibration variables, are a function of…
There has been much recent interest in application of the pool-adjacent-violators (PAV) algorithm for the purpose of calibrating the probabilistic outputs of automatic pattern recognition and machine learning algorithms. Special cost functions, known as proper scoring rules form natural objective functions to judge the…
Solves the equity premium puzzle without calibrated values.
problem Equity premium puzzle in finance.
method Derived new model from 4 different equations, found subjective time discount factor and coefficient of relative risk aversion.
result Calculated values and risk attitude determination align with empirical literature.
New method calibrates probabilistic regression models without restrictive assumptions.
problem Ensuring predictive distributions accurately reflect true uncertainty.
method Nonparametric re-calibration algorithm based on conditional kernel mean embeddings.
result Consistently outperforms prior re-calibration approaches across various benchmarks.
Establishes a condition for multiclass classification-calibration of Gamma-Phi losses.
problem Ensuring classification-calibration of multiclass Gamma-Phi losses.
method Develops a general sufficient condition for classification-calibration of Gamma-Phi losses.
result Proves the first family of nonconvex multiclass surrogate losses for which classification-calibration has been fully justified.
CCAC calibrates DNN classifiers on OOD datasets by separating mis-classified samples.
problem Calibrating DNN classifiers on out-of-distribution datasets is challenging.
method CCAC introduces an auxiliary class to map DNN output to calibrated confidence, separating mis-classified from correctly classified samples.
result CCAC consistently outperforms prior methods on various DNN models, datasets, and applications.
Meta-learning reduces set prediction size in conformal prediction for few-shot calibration.
problem Inefficient set prediction in conformal prediction for limited training data.
method Meta-learning approach using cross-validation-based conformal prediction.
result Meta-learning scheme reduces set prediction size and preserves formal guarantees.
Bayesian deep learning improves accuracy and calibration without sacrificing scalability.
problem Bayesian inference's potential for deep neural networks.
method Marginalization over optimization, using neural networks' inherent structure and inductive biases.
result Improvements in accuracy and calibration compared to standard training methods.
Bayesian method calibrates local volatility with Gaussian processes.
problem Calibrating local volatility models is challenging.
method Bayesian inference with Gaussian process priors.
result Rich probabilistic model of local volatility with uncertainty.
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.
A simple method treats heteroscedastic variance variatively, improving model calibration and sample quality.
problem Brittle optimization impacts model likelihoods for mean and variance estimation.
method Proposes a variational approach to heteroscedastic variance, improving predictive mean and variance calibration.
result The proposed method significantly improves parameter calibration and sample quality for regression and VAEs.
The local volatility model is a widely used for pricing and hedging financial derivatives. While its main appeal is its capability of reproducing any given surface of observed option prices---it provides a perfect fit---the essential component is a latent function which can be uniquely determined only in the limit of i…
New AI approach improves quantum device calibration by leveraging prior scientific discoveries.
problem Lack of abundant data in scientific disciplines hinders model generalizability.
method Introduces a new machine learning approach that combines prior scientific knowledge with data.
result Accuracy in predicting quantum device energy spectrum surpasses current state-of-the-art by over 20%.
HS-BQR extends horseshoe prior for Bayesian quantile regression.
problem Estimating quantiles in high-dimensional data with bias and error.
method Horseshoe prior for Bayesian quantile regression with a fast sampling algorithm.
result HS-BQR outperforms other shrinkage priors in coefficient bias and forecast error.
A fast calibration method for rough volatility models with jumps.
problem Calibrating stochastic volatility models to market data efficiently.
method Structure-preserving approach: split pricing formula, precompute data-independent integrals, and approximate market-dependent remainder with neural networks.
result Calibration achieves high accuracy and speed, and a pure-jump rough volatility model adequately captures VIX dynamics.
New method learns SIMs with arbitrary monotone activations without strong distributional assumptions.
problem Learning Single-Index Models with arbitrary monotone activations.
method Based on omniprediction with calibrated multiaccuracy and Bregman divergences.
result First agnostic learning result for SIMs with arbitrary monotone activations.
Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not explicitly measure the uncertainties. This is conceptually similar to heteroscedastic ne…
This paper learns prior models from indirect data efficiently.
problem Learning prior models from indirect data in Bayesian inversion.
method Generative model of prior as pushforward of Gaussian in latent space, learned by minimizing loss function.
result Efficient residual-based neural operator approximation for forward model learning.
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.
A new method for designing accurate emulators using deep learning with interval calibration.
problem Designing accurate emulators for scientific processes with modern machine learning methods.
method Learn-by-Calibrating (LbC) approach based on interval calibration.
result Significant improvements in generalization error over widely-used loss functions.
The resolution and calibration of pure spectra of minority components in measurements of chemical mixtures without prior knowledge of the mixture is a challenging problem. In this work, a combination of band target entropy minimization (BTEM) and target partial least squares (T-PLS) was used to obtain estimates for sin…
Estimates calibration error under label shift without labels.
problem Ensuring model reliability in the face of dataset shift without access to labels.
method Importance re-weighting of the labeled source distribution to estimate calibration error under label shift.
result Effective and reliable CE estimation with respect to the shifted target distribution.
Posterior SBC validates inference conditionally on observed data.
problem Validating inference for specific observed data.
method Simulation-based calibration checking (SBC) adapted to use posterior parameters.
result Validates inference conditionally on observed data.
New method calibrates multi-class predictions efficiently without sacrificing accuracy.
problem Efficiently calibrating multi-class predictions without sacrificing accuracy.
method Formulated robust projected smooth calibration and new recalibration algorithms.
result Achieves strong guarantees for binary classification tasks with polynomial complexity.
We introduce a fast model based deep learning approach for calibrationless parallel MRI reconstruction. The proposed scheme is a non-linear generalization of structured low rank (SLR) methods that self learn linear annihilation filters from the same subject. It pre-learns non-linear annihilation relations in the Fourie…
DNAMite creates interpretable, calibrated survival analysis models.
problem Limited interpretability in survival analysis models, especially for healthcare applications.
method Feature discretization and kernel smoothing in embedding module for flexible shape functions.
result DNAMite produces calibrated shape functions interpretable as contributions to cumulative incidence function.
Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust, and efficient measures of uncertainty are crucial. In this paper, we propose a novel method for training non-Bayesian NNs to estimate a continuous target as well as its associated evidence in order …