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 AI error correctors improve classifier performance with provable guarantees.
problem Improving AI classifier performance with scarce training data.
method Weakly supervised AI error correctors with performance guarantees.
result Provable performance guarantees for AI error correction.
This study investigates how Decision-Focused Learning improves stock return predictions for better portfolio optimization.
problem The challenge of precise expected returns estimation in mean-variance optimization.
method Investigates Decision-Focused Learning (DFL) to adjust stock return prediction models for MVO.
result DFL tilts prediction errors by the inverse covariance matrix, leading to systematic prediction biases in portfolio optimization.
This work bounds classification error in machine learning for low Bayes error conditions.
problem Understanding the error mismatch between Bayes error and model-based classification error.
method Applying classification error bounds to study the relationship with Kullback-Leibler divergence and proposing a linear approximation for low Bayes error conditions.
result A linear approximation of the classification error bound for low Bayes error conditions is proposed.
Optimal statistical test for identifying edges in Gaussian graphical models.
problem Identifying the correct edges in Gaussian graphical models from a sample.
method Developed a Neyman-type multiple decision procedure to minimize the combined error rates of Type I and Type II errors.
result The developed procedure is optimal, minimizing the linear combination of Type I and Type II error rates.
Paper designs decision trees for minimizing misclassification in crowdsourcing.
problem Minimizing misclassification in crowdsourcing systems with unreliable workers.
method Proposes two algorithms for designing decision trees based on minimizing the probability of misclassification and entropy.
result Demonstrates improved error performance through worker assignment to different tests.
Paper evaluates how forecast errors affect optimal utilisation in production planning.
problem Forecast errors impact optimal utilisation in production planning.
method Simulation and mixed integer programming for stochastic demand.
result Forecast errors significantly affect optimal costs in production planning.
Study on error probabilities of machine learning classification techniques using large deviations theory.
problem Performance analysis of machine learning binary classification techniques.
method Large deviations theory applied to Data-Driven Decision Function (D3F) for error probability analysis.
result Classification error probabilities vanish exponentially, with an asymptotic formula providing precise error rate estimates.
The study analyzes how covariance estimation errors affect the global minimum-variance portfolio under heavy-tailed distributions.
problem The impact of covariance estimation errors on the global minimum-variance portfolio under heavy-tailed distributions.
method Characterization of covariance-estimation error's effect on GMVP suboptimality, derivation of regret identity and bound, application to heavy-tailed returns.
result The decision geometry of GMVP regret is invariant to a (p-1)-dimensional projection of the error matrix, with invariance to the covariance-scale direction as an exact special case.
ETD algorithm provides error bounds for off-policy evaluation.
problem Off-policy evaluation in Markov decision processes.
method Introduced the emphatic temporal differences (ETD) algorithm and showed that its underlying fixed-point equation involves a contraction operator.
result First error bounds for off-policy evaluation algorithms under general policies.
Algorithm learns decision trees from noisy data.
problem Learning stochastic decision trees from corrupted samples.
method Quasipolynomial-time algorithm for adversarial noise.
result Returns a hypothesis with error within 2η+ε of optimal. Active learning improves decision-making from imbalanced observational data.
problem Reliability of prediction-based decisions in imbalanced observational data.
method Estimate Type S error rate to assess reliability, use active learning to collect new data.
result Active learning improves decision-making reliability in imbalanced data.
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.
Paper integrates LLMs into portfolio optimization to improve decision quality.
problem Suboptimal portfolio decisions due to mismatch between prediction and decision quality.
method Integrates LLMs with decision-focused learning, using attention mechanism to process asset relationships and macro variables.
result Model consistently outperforms state-of-the-art deep learning models in portfolio optimization.
SRO optimizes decisions against worst-case sampler induced by generative models.
problem Operational uncertainty shifts from explicit probability law to sampler induced by learned generators.
method SRO optimizes decisions against the worst-case sampler induced by perturbing the learned generator.
result Empirical worst-case objective provides high-probability upper certificate for true population objective.
Boosted decision stumps and trees are made robust against adversarial attacks efficiently.
problem Efficiently making boosted decision stumps and trees robust against adversarial attacks.
method Exact min-max robust loss and test error computation for decision stumps, upper bound optimization for trees.
result State-of-the-art robust test error rates for boosted trees on various datasets.
The paper improves car leasing pricing by forecasting residual values with asymmetric cost functions.
problem Forecasting residual values for leasing contracts with asymmetric cost functions.
method Develops forecasting models with asymmetric cost functions to address the asymmetric costs of forecast errors.
result Forecasting with asymmetric cost functions reduces decision costs by about 8% compared to standard models.
Decision tree predictions improve with better split point interpolation methods.
problem Interpolation errors in decision tree models can lead to misclassification.
method Comparing alternative split point interpolation methods and quantile transformation.
result Quantile transformation reduces interpolation error by up to half.
Improved decision tree learning guarantees for complex functions.
problem Achieving provable guarantees for decision tree induction with complex target functions.
method Introduces a new splitting criterion that considers correlations between target function and subsets of attributes.
result Proves provable guarantees for all target functions with respect to the uniform distribution, circumventing previous impossibility results.
Decision trees improve decision-making by optimizing predictions of unknown parameters.
problem Optimizing decisions based on predicted unknown parameters.
method SPO Trees (SPOTs) for training decision trees under the SPO loss function.
result SPOTs provide higher quality decisions and significantly lower model complexity compared to other machine learning approaches.
We introduce the speculate-correct method to derive error bounds for local classifiers. Using it, we show that k nearest neighbor classifiers, in spite of their famously fractured decision boundaries, have exponential error bounds with O(sqrt((k + ln n) / n)) error bound range for n in-sample examples.
New method controls false discoveries in real-time data streams.
problem Online testing of hypotheses with strict error constraints and no future data.
method Structure-adaptive sequential testing (SAST) with alpha-investment algorithm.
result Substantial power gain over existing online testing rules.
Paper uses DFL to optimize portfolio risk and outperforms conventional methods.
problem Optimizing portfolio risk and return under uncertainty.
method Decision-focused learning (DFL) to derive global minimum variance portfolio (GMVP).
result DFL-based methods consistently deliver superior decision performance in portfolio optimization.
Proposes a new method for decision-aware learning in optimization.
problem Contextual linear optimization with cost prediction errors.
method Reweighing prediction error by decision regret for decision-aware predictor.
result Improves over predict-then-optimize framework for misspecified models.
This paper infers parameters of multiobjective decision making from noisy data.
problem Inferring parameters of multiobjective decision making from noisy data.
method Developed a data-driven inverse optimization formulation to explicitly infer parameters of a multiobjective decision making problem.
result Demonstrates strong capacity in estimating critical parameters and understanding preference distributions over multiple criteria.
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.
The paper reduces estimation error in predicting borrower repayment by accounting for lender's credit decisions.
problem Estimation error in predicting borrower repayment due to confounding effects.
method Proposes new estimators to reduce estimation error, combining theoretical analysis and numerical testing.
result The proposed estimators are unbiased, consistent, and robust, showing substantial reduction in estimation error.
GRAF uses global partitioning to improve ensemble classifier performance.
problem Improving ensemble classifier performance.
method GRAF extends oblique decision trees to global partitioning.
result GRAF reduces generalization error and improves performance on benchmark datasets.
This paper proposes a new VoI analysis framework for complex decision problems.
problem Optimizing resource allocation for information collection in decision-making under uncertainty.
method Surrogate-based framework for Value of Information analysis, integrating knowledge sharing and adaptive training.
result Accurate and robust estimates of VoI with fewer model evaluations compared to state-of-the-art methods.
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.
Random forests improve by using out-of-bag samples for post-pruning.
problem Improving the generalization error of random forests.
method Post-pruning using out-of-bag samples to improve decision trees and random forest size.
result Consistent decrease in forest size with no significant loss in accuracy.
This paper analyzes stability of decision trees and logistic regression.
problem Stability of decision trees and logistic regression is analyzed to understand their performance and sensitivity.
method Two stability notions (hypothesis and pointwise hypothesis stability) are derived for decision trees and logistic regression. The stability of decision trees depends on the number of leaves, while for logistic regression, it depends on the smallest eigenvalue of the Hessian matrix. Upper bounds on generalization error are constructed.
result Logistic regression is not a stable learning algorithm.
Proposes a method to quantify uncertainty in DNN models for discrete inputs.
problem Uncertainty quantification for DNN models with categorical and discrete feature variables.
method Develops a mathematical framework to quantify prediction uncertainty from discrete input noise and model parameters.
result Identifies risk-sensitive cases prone to misclassification due to discrete predictor errors.
The paper tackles decision making problems with funnel structure in email marketing campaigns.
problem Decision making challenges in systems with funnel structure, where fewer observations are received from deeper layers.
method Formulated as a contextual bandit with funnel structure and developed a multi-task learning algorithm.
result Our algorithms offer significant improvement over previous methods in email marketing campaigns.
Paper tackles identifying an odd arm in a multi-armed bandit with restless Markov processes and trembling hand.
problem Identifying an odd arm in a multi-armed bandit with restless Markov processes and trembling hand.
method Derive asymptotic lower bound on expected time to identify the odd arm, stitch together parameterised solutions to MDPs.
result First known asymptotic lower bound on expected time to identify the odd arm, with vanishing error probability.
The paper shows how to learn near-optimal behavior in reinforcement learning with rich observations.
problem Learning near-optimal behavior in reinforcement learning with rich observations and function approximation.
method Introduces a new model called contextual decision processes and a new algorithm that engages in systematic exploration to learn these processes with low Bellman rank.
result The algorithm provably learns near-optimal behavior with a number of samples that is polynomial in all relevant parameters.
Decision-alignment evaluates uncertainty quantification for decision-relevant UQ
problem Evaluation of uncertainty quantification metrics
method Introduce decision-alignment
result Proper scoring rules align with decision utility
Autoencoder neural network is implemented to estimate the missing data. Genetic algorithm is implemented for network optimization and estimating the missing data. Missing data is treated as Missing At Random mechanism by implementing maximum likelihood algorithm. The network performance is determined by calculating the…
An assistant learns to mediate decisions between humans and experts, balancing risk and learning.
problem Learning to mediate decisions between imperfect humans and expert knowledge.
method Formalizes online decision mediation, proposes a policy to balance immediate loss and future generalization.
result Consistent gains over benchmarks in decision-making performance.
Zero-error classifiers use object distances to classify without errors.
problem Classifying objects based on non-Euclidean distances.
method Derive conditions for zero-error classifiers using distances to training samples.
result Zero-error decision boundary is a continuous function of distances to training samples under certain conditions.
Sparse MDP with entropy regularization improves reinforcement learning performance.
problem Improving reinforcement learning policies with sparse and multi-modal distributions.
method Proposes a sparse Markov decision process with causal sparse Tsallis entropy regularization.
result The proposed method achieves a constant performance error bound, outperforming soft MDPs.
Improves generative models for cost-sensitive decisions.
problem Generative models lack awareness of decision costs.
method Integrates a decision loss into the training objective.
result Improves cost-sensitive forecast accuracy.
Automated medical protocol uses neural networks and decision trees.
problem Improving healthcare delivery through automated decision-making.
method Hybrid model combining neural networks and decision trees.
result Effective early decisions for patient care.
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.
Study explores loss design for decision trees to improve robustness against noisy labels.
problem Improving decision tree robustness to noisy labels.
method Investigated loss correction and symmetric losses, found ineffective.
result Other loss design directions need exploration for robust decision trees.
A new framework detects forecast model inadequacies using online monitoring of forecast errors.
problem Inaccurate forecasts lead to poor decision-making in complex models.
method Sequential changepoint techniques on forecast errors for real-time identification of process changes.
result The framework identifies shifts in forecast errors faster than in the original models, indicating process changes.
Improved model-free reinforcement learning with decision-estimation coefficient.
problem Interactive decision making, including structured bandits and reinforcement learning.
method Combining Estimation-to-Decisions with optimistic estimation to achieve better regret bounds.
result Regret bounds for model-free reinforcement learning with value function approximation.