New decision-theoretic calibration error metric improves prediction reliability.
problem Improving the reliability of predictions for decision-making.
method Proposed Calibration Decision Loss (CDL) and an efficient algorithm to achieve near-optimal CDL.
result Near-optimal CDL guarantees vanishing payoff loss from miscalibration.
Post-processing predictors reduces calibration errors for decision-making.
problem Predictors with low calibration error for machine learning may have high error for decision-making.
method Post-processing with ε distance to calibration adds noise to make predictions differentially private.
result Post-processing achieves O(√ε) ECE and CDL, asymptotically optimal.
New approach calibrates predictions for better decision-making.
problem Achieving reliable predictions for multi-class problems is hard.
method Introduces decision calibration, a new approach to calibrate predictions.
result Designs a recalibration algorithm that makes predictions reliable for decision-making.
The paper addresses decision making with partially calibrated forecasts, offering a robust approach.
problem Developing a decision-making strategy for forecasts that are only partially calibrated.
method A minimax approach to mapping predictions to actions, considering worst-case distributions.
result The minimax optimal decision rule is to trust predictions and act accordingly, even for partially calibrated forecasts.
New algorithms achieve decision calibration without sample complexity dependent on feature dimension.
problem Achieving decision calibration for nonlinear loss functions with polynomial sample complexity.
method Developed smooth relaxation of decision calibration, enabling dimension-free algorithms.
result Efficient algorithms post-process predictors to satisfy decision calibration without worsening accuracy.
New method improves decision-making accuracy without complex calculations.
problem Improving decision-making accuracy in machine learning.
method Introducing a new measure called calibration decision loss (CDLK) for structured families of post-processing functions. result Proves upper and lower bounds for natural classes K of post-processing functions. Gini index needs auto-calibration for consistent decision-making.
problem Gini index's inconsistency in decision-making.
method Restrict Gini index to auto-calibrated regression models.
result Gini index becomes strictly consistent with auto-calibration.
Develop a decision-calibrated conformal framework for pacing decisions in streaming advertising.
problem Pacing decisions in streaming advertising
method Develop a decision-calibrated conformal framework
result The proposed score is the smallest valid uncertainty measure that uniformly protects all deployable pacing policies.
A new calibration metric bridges testability and actionability.
problem Combining testability and actionable insights for forecast probabilities.
method Cutoff Calibration Error (CCE) that assesses calibration over intervals of forecasted probabilities.
result Cutoff Calibration Error is both testable and actionable.
Unified calibration metrics improve forecast sharpness and accuracy.
problem Improving the sharpness of probabilistic forecasts while maintaining calibration.
method Kernel-based calibration metrics that unify and generalize existing methods for classification and regression.
result Enhanced calibration, sharpness, and decision-making across various tasks.
Improves survival prediction model calibration for better individual decision-making.
problem Survival prediction's marginal and conditional calibration issues.
method Conformal prediction using individual survival probabilities.
result Effective marginal and conditional calibration without compromising discrimination.
Linguistic calibration improves long-form text confidence.
problem LMs hallucinate, leading to suboptimal decisions.
method Defining linguistic calibration, training framework, reinforcement learning.
result Llama 2 7B is significantly more calibrated than baselines.
The paper optimizes forecasting for risk-adjusted decisions under trading frictions.
problem Optimizing forecasting accuracy for investment decisions in the presence of transaction costs.
method Develops a utility-weighted calibration criterion to minimize decision loss net of costs.
result Utility-weighted calibration reduces decision loss by over 30% and improves Sharpe ratio.
Decision-calibrated prediction sets improve power system operations by reducing unnecessary costs.
problem Balancing operating costs and reliability in power systems with renewable uncertainty.
method Learn conditional prediction sets as sub-level sets of norm-based score functions, calibrate uncertainty sets based on reliability of downstream decisions.
result Decision-calibrated sets lead to more efficient operations with smaller uncertainty sets and lower costs compared to standard coverage-based calibration.
New truthful calibration errors improve model ranking in multiclass prediction.
problem Non-truthful calibration errors can mislead model comparisons.
method Introduced perfectly truthful calibration errors for multiclass predictions.
result Truthful calibration errors preserve decision-theoretic dominance and stabilize model rankings.
Loss-calibrated EP improves Bayesian decision-making by focusing on utility-sensitive posterior approximations.
problem Bayesian decision-making under asymmetric utility functions.
method Loss-calibrated expectation propagation (Loss-EP) that tilts the posterior towards higher utility decisions.
result Loss-EP can capture useful information for decision-making under asymmetric penalties.
This paper establishes the asymptotic consistency of the {\it loss-calibrated variational Bayes} (LCVB) method. LCVB was proposed in~\cite{LaSiGh2011} as a method for approximately computing Bayesian posteriors in a `loss aware' manner. This methodology is also highly relevant in general data-driven decision-making con…
Survey on calibration in machine learning, viewing it as indistinguishability.
problem Evaluating continuous probability predictions in discrete outcome settings.
method Defining and measuring calibration error through indistinguishability.
result Calibration measures quantify distinguishability between hypothesized and real-world outcomes.
The paper corrects Bayesian neural network approximations to improve decision quality.
problem Inaccurate posterior approximations in Bayesian neural networks lead to suboptimal decisions.
method Develops methods to calibrate approximate posterior predictive distributions for better decision making.
result Empirically produces higher quality decisions compared to previous methods.
Post-hoc calibration of neural networks using g-Layers proves theoretical justification.
problem Ensuring the confidence of neural network decisions in real-world applications.
method Proves theoretical justification for post-hoc calibration methods by adding g-Layers and minimizing NLL.
result Proves that adding g-Layers and minimizing NLL can lead to a calibrated network.
The paper improves Bayesian optimization by calibrating uncertainty estimates.
problem Improper uncertainty estimates in Bayesian optimization when data is non-stationary.
method Proposes online learning algorithms to maintain calibration on non-i.i.d. data and integrates them into Bayesian optimization.
result Calibrated Bayesian optimization converges to better optima in fewer steps.
Develops a method to make predictions more informative without sacrificing accuracy.
problem Tension between well-calibrated and bold predictions.
method Bayesian model selection-based approach for assessing calibration and maximizing boldness.
result Maximally emboldening predictions while maintaining desired level of calibration.
New calibration measure SCDL improves trust in AI predictions.
problem Improving trust in AI predictions by ensuring they are both actionable and testable.
method Introducing SCDL, a new calibration measure that is fully actionable and testable.
result SCDL is the first calibration measure that is fully actionable and testable.
New concept of proper-calibeating extends classic calibrated forecasts to proper scoring rules.
problem Defining and extending calibrated forecasts to proper scoring rules.
method Extending the concepts of calibrated and calibeating forecasts to proper scoring rules and proving their properties.
result Proper-calibration always implies calibration, but proper-calibeating does not necessarily imply calibeating.
Tree-based models biased when trained on imbalanced data, requiring new calibration methods.
problem Bias in tree-based models trained on imbalanced datasets.
method Analytical calibration of random forest models, demonstrating bias in decision trees.
result Calibrating tree-based models on imbalanced data negatively impacts predictions, especially for the minority class.
Bayesian GBMs improve predictive uncertainty calibration for tabular data.
problem Lack of well-calibrated predictive uncertainties in gradient boosting machines.
method Variational inference with soft decision trees.
result Variational soft GBMs provide useful uncertainty estimates and maintain good predictive performance.
Bayesian decision theory outlines a rigorous framework for making optimal decisions based on maximizing expected utility over a model posterior. However, practitioners often do not have access to the full posterior and resort to approximate inference strategies. In such cases, taking the eventual decision-making task i…
Boosted decision trees typically yield good accuracy, precision, and ROC area. However, because the outputs from boosting are not well calibrated posterior probabilities, boosting yields poor squared error and cross-entropy. We empirically demonstrate why AdaBoost predicts distorted probabilities and examine three cali…
Score calibration enables automatic speaker recognizers to make cost-effective accept / reject decisions. Traditional calibration requires supervised data, which is an expensive resource. We propose a 2-component GMM for unsupervised calibration and demonstrate good performance relative to a supervised baseline on NIST…
Graph Neural Networks (GNNs) have proven to be successful in many classification tasks, outperforming previous state-of-the-art methods in terms of accuracy. However, accuracy alone is not enough for high-stakes decision making. Decision makers want to know the likelihood that a specific GNN prediction is correct. For …
New methods help calibrate complex ABMs more efficiently.
problem Calibrating parameters in complex ABMs is challenging.
method Integrates different sampling methods and surrogate models.
result Surrogate assisted methods perform better than standard methods.
This paper argues against using calibration metrics for assessing posterior probabilities and proposes expected proper scoring rules instead.
problem The assessment of posterior probabilities generated by machine learning classifiers using calibration metrics is flawed and should be replaced with expected proper scoring rules.
method The paper reviews proper scoring rules from a practical perspective, explains why expected PSRs are a principled measure of posterior quality, and introduces a new calibration metric called calibration loss.
result Calibration loss is superior to expected calibration error and expected score divergence calibration metrics for assessing posterior probabilities.
The study quantifies decision-making risks from suboptimal classifiers and proposes methods to reduce these risks.
problem Excess risk in decision-making from suboptimal probabilistic classifiers.
method Analytical expressions and upper/lower bounds for excess risk, calibration curve estimation, grouping loss estimator.
result Identifies regimes where recalibration alone or post-training is more effective.
Probability estimates generated by boosting ensembles are poorly calibrated because of the margin maximization nature of the algorithm. The outputs of the ensemble need to be properly calibrated before they can be used as probability estimates. In this work, we demonstrate that online boosting is also prone to producin…
A popular methodology for building binary decision-making classifiers in the presence of imperfect information is to first construct a non-binary "scoring" classifier that is calibrated over all protected groups, and then to post-process this score to obtain a binary decision. We study the feasibility of achieving vari…
This paper calibrates Gaussian process predictive distributions for Bayesian optimization to improve sampling decisions.
problem Lower-tail miscalibration in GP predictive distributions affects BO sampling decisions.
method Introduces goal-oriented calibration for GP predictive distributions below a threshold t. result Post-hoc method tcGP improves lower-tail calibration and BO performance.
New framework calibrates models to control risk under performativity.
problem Calibrating models to ensure reliable decision-making under performativity.
method Iteratively refined calibration process for different risk measures and tail bounds.
result Statistically rigorous risk control under performativity demonstrated.
Efficiently calibrates epidemiological models using Bayesian optimization.
problem Calibration of complex epidemiological models is computationally expensive and challenging.
method Graybox Bayesian optimization scheme leveraging Gaussian processes and functional structure of compartmental models.
result Proposed methods achieve efficient calibration and improved performance compared to existing schemes.
New framework calibrates decision robustness using inverse conformal risk control.
problem Inadequate robustness levels in decision-making due to ad hoc choices.
method Constructs valid estimators to trace miscoverage-regret Pareto frontier.
result Provides distribution-free, finite-sample guarantees on robustness levels.
New loss improves DNN calibration without sacrificing accuracy.
problem Overfitting and overconfident predictions in DNNs.
method Proposes a new loss function inspired by Bayes decision theory.
result Improves DNN calibration without compromising accuracy.
Survey on assessing and improving classifier calibration for better decision making.
problem Ensuring classifiers correctly quantify prediction uncertainty.
method Overview of principles, methods, and evaluation metrics for calibration.
result New methods and extensions from binary to multiclass settings.
Recently, Deep Neural Networks (DNNs) have been achieving impressive results on wide range of tasks. However, they suffer from being well-calibrated. In decision-making applications, such as autonomous driving or medical diagnosing, the confidence of deep networks plays an important role to bring the trust and reliabil…
The paper examines how calibration affects the interpretability of ML models in diabetes screening.
problem Interpreting complex ML models in healthcare, especially in diabetes screening.
method Examined the impact of model calibration on interpretability using three visualization techniques.
result Calibrated models provide clearer cause-effect relationships in ML predictions.
Study improves neural network calibration for drug discovery.
problem Improper calibration of neural network predictions in drug discovery.
method Compared different metrics for model hyperparameter tuning and proposed Bayesian Linear Probing (BLP) method.
result Bayesian Linear Probing (BLP) improves model calibration and accuracy.
Safe autonomous decisions made with machine learning predictions using Conformal Decision Theory.
problem Safe decisions from imperfect machine learning predictions.
method Conformal Decision Theory framework for producing safe decisions.
result Safe decisions with provable statistical guarantees of low risk.
New method calibrates models under covariate shifts.
problem Calibration of models can be lost under covariate shifts.
method Importance sampling based approach.
result Efficacy demonstrated on real-world and synthetic datasets.
The paper addresses the difficulty of decision makers trusting AI-assisted predictions and proposes a method to improve confidence values.
problem Decision makers struggle to trust AI-assisted predictions based on confidence values.
method The paper investigates why decision makers have difficulties and proposes a method to construct more useful confidence values.
result Multicalibration with respect to the decision maker's confidence on her own predictions is a sufficient condition for alignment, leading to better decisions.
New method combines multiple data sources for optimal decision-making with limited outcomes.
problem Optimal decision-making with limited outcome data from multiple heterogeneous sources.
method Calibrated optimal decision-making method leveraging common intermediate outcomes.
result Proposed estimator of conditional mean outcome is asymptotically normal and more efficient.