Simplifies machine learning validation using kNN and conditional probability algorithms.
problem Validating machine learning models in practical applications.
method Reformulated regression and classification problems using kNN and conditional probability algorithms.
result Online capability and reduced memory usage compared to kNN.
Cross-validation is the workhorse of modern applied statistics and machine learning, as it provides a principled framework for selecting the model that maximizes generalization performance. In this paper, we show that the cross-validation risk is differentiable with respect to the hyperparameters and training data for …
A method to select validation data from a dataset using statistical criteria.
problem Selecting a validation basis from a full dataset for machine learning model validation.
method Adopting a 'design of experiments' point of view and using statistical criteria, particularly Maximum Mean Discrepancy criteria.
result The 'support points' concept is particularly relevant for selecting validation data.
Machine learning detects survey validity from user behavior.
problem Detecting valid responses in web surveys.
method Uses mouse activity and machine learning models (LSTM, HMM).
result Predicts survey validity without analyzing specific answers.
Valid inference from data and predictions.
problem Valid statistical inference with machine learning predictions.
method Framework for valid inference using machine learning predictions.
result Valid confidence intervals without assumptions on predictions.
The paper assesses quality measures for machine learning models using cross-validation.
problem Evaluating the accuracy and robustness of quality measures for machine learning models.
method Cross-validation approach to estimate prediction error and quantify explained variation. Confidence bounds and local quality measures derived from residuals.
result The reliability and robustness of quality measures are assessed through numerical examples and confidence bounds.
Machine learning improves official statistics but needs rigorous validation.
problem Lack of methodological robustness in machine learning for official statistics.
method Total Machine Learning Error (TMLE) framework to validate ML models.
result TMLE addresses representativeness and measurement errors in ML models.
Active learning method improves local model validity estimation.
problem Ensuring local model validity in machine learning applications.
method Learning model error to estimate local validity using active learning.
result The proposed method can estimate local validity with a small amount of data.
Interpretable ML helps discover insights from big data.
problem Validating data-driven discoveries from complex datasets.
method Statistical and machine learning techniques for interpretable models.
result Challenges in validating data-driven discoveries remain.
Machine learning models trained on indirect data labels can fail on real-world examples.
problem Validity issues in machine learning when target labels are indirectly defined.
method Identification of problematic datasets and models using a general procedure.
result Machine learning models trained on indirect data labels will fail on real-world examples.
Machine learning methods may have the potential to significantly accelerate drug discovery. However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should be benchmarked and validated. We reanalyze the data generated by a recently pub…
Unified taxonomy for ML uncertainty in physics, validated.
problem Uncertainty quantification in machine learning for physics.
method Unified taxonomy, principled validation tools.
result Illustrated validation tools with examples.
Causal ML methods failed to validate their personalized treatment effects in two large trials.
problem Validating causal machine learning methods for personalized treatment effects in precision medicine.
method Assessed 17 mainstream causal heterogeneity ML methods using two large randomized controlled trials.
result None of the ML methods reliably validated their performance, internal or external, showing significant discrepancies between training and test data.
Paper tackles circularity issues in machine learning predictions.
problem Circularity problems in machine learning predictions.
method Not specified in the abstract.
result Not specified in the abstract.
K-fold CV improves machine learning model selection but faces challenges with small datasets.
problem Challenges in validating machine learning models, especially with small datasets.
method K-fold cross-validation with K-fold CUBV (Upper Bound of the actual risk) and Upper Bound of the actual risk for linear classifiers.
result K-fold CUBV is a robust criterion for detecting effects and validating accuracy values from machine learning models.
This study revisits UQ validation methods based on consistency and adaptivity concepts.
problem Lack of comprehensive validation methods for UQ metrics across input feature ranges.
method Revisit and extend common validation methods for UQ metrics based on consistency and adaptivity concepts.
result Improved understanding and capabilities of UQ metrics validation methods.
We study the problem of collaborative machine learning markets where multiple parties can achieve improved performance on their machine learning tasks by combining their training data. We discuss desired properties for these machine learning markets in terms of fair revenue distribution and potential threats, including…
Researchers validate ML scenario generators by checking dependencies and detecting memorization effects.
problem Validation of machine learning-based scenario generators differs from classical methods due to data-driven dependencies.
method Two novel validation aspects: checking dependencies and detecting memorization effects. Novel memorization ratio introduced.
result Validation methods successfully detect dependencies and memorization effects in ML-based scenario generators.
TBAL reduces manual annotation but requires validated data.
problem Creating large, high-quality labeled datasets.
method Threshold-based auto-labeling using human validation data.
result Sample complexity bounds on validation data needed.
The paper uses machine learning to forecast macroeconomic outcomes with high-dimensional data.
problem Forecasting the full conditional distribution of macroeconomic outcomes.
method Systematically integrating three key principles: high-dimensional data with regularization, rigorous out-of-sample validation, and incorporating nonlinearities.
result Regularization via shrinkage is essential to control model complexity, while nonlinearities yield limited improvements in predictive accuracy.
Method improves treatment effect estimation in randomized experiments.
problem Estimating distributional treatment effects in randomized experiments.
method Distributional regression framework with machine learning for variance reduction.
result The proposed method reduces variance of distributional treatment effect estimators.
The paper clarifies conditions for using benchmark scores in machine learning.
problem Using benchmark scores to draw scientific inferences about learning problems.
method Developing conditions of construct validity inspired by psychological measurement theory.
result Clarifies conditions under which benchmark scores support diverse scientific claims.
Machine learning models perform better with location coordinates alone, not Moran Eigenvectors.
problem Improving machine learning models for spatial data.
method Examined Moran Eigenvectors as additional spatial features in machine learning models using synthetic datasets.
result Machine learning models using only location coordinates achieve better accuracies than eigenvector-based approaches.
Zellner (1988) modeled statistical inference in terms of information processing and postulated the Information Conservation Principle (ICP) between the input and output of the information processing block, showing that this yielded Bayesian inference as the optimum information processing rule. Recently, Alemi (2019) re…
New method uses weak labels to create valid confidence sets for predictions.
problem Lack of labeled data in machine learning models.
method Developed a conformal prediction framework to provide valid predictive confidence sets using weakly labeled data.
result New coverage definition allows for tighter and more informative (but valid) confidence sets.
SaML guides ML models to avoid survey biases.
problem ML models trained on survey data often ignore survey design metadata.
method Nine-step guideline for incorporating survey design metadata in ML lifecycle.
result SaML provides valid population inference from survey data.
Surveying machine learning methods for economic forecasting.
problem Improving accuracy of economic forecasts using machine learning.
method Nowcasting, textual data, panel and tensor data, high-dimensional Granger causality tests, time series cross-validation, classification with economic losses.
result Recent advances in machine learning methods enhance economic forecasting accuracy.
The correct use of model evaluation, model selection, and algorithm selection techniques is vital in academic machine learning research as well as in many industrial settings. This article reviews different techniques that can be used for each of these three subtasks and discusses the main advantages and disadvantages …
Methodology creates holdout and test/train sets for ML studies, preserving data for future research.
problem Preserving data for future research studies that are analysis-naive.
method Modification of k-fold cross-validation, randomization, and three-way split (holdout, test, training).
result Efficiently creates holdout and test/train sets without forcing.
Interpretable machine learning uncovers ESG's explanatory power on equity returns across sectors and capitalizations.
problem Explaining equity returns beyond market factors using ESG data.
method Interpretable machine learning models, cross-validation scheme, random company-wise validation.
result Gradient boosting models explain unaccounted price returns, with ESG data outperforming basic fundamental features.
LOOCV is often useful for analyzing small, structured experimental designs.
problem The effectiveness of cross-validation in analyzing designed experiments.
method Empirical study comparing LOOCV and other model selection methods.
result LOOCV is often useful in the analysis of small, structured experimental designs.
Machine Learning improves macroeconomic forecasting by capturing nonlinearities.
problem Improving macroeconomic forecasting accuracy.
method Study four features (nonlinearities, regularization, cross-validation, loss function) in data-rich and data-poor environments.
result Nonlinearity is the key to improving forecasting accuracy.
Flexible framework integrates machine learning and DRO for uncertain parameter prediction.
problem Limited joint observations of uncertain parameters and covariates.
method Wasserstein, sample robust optimization, and phi-divergence-based ambiguity sets.
result Validation of theoretical and practical benefits in limited data scenarios.
The paper provides a method to find optimal machine learning model parameters with confidence.
problem Finding optimal machine learning model parameters that generalize well to the entire population.
method Constructs valid confidence sets for the optimal parameter using only training data.
result Valid confidence sets for optimal machine learning model parameters can be generated using bootstrapping techniques.
The paper improves confidence intervals for test error using cross-validation.
problem Improving confidence intervals for test error in machine learning.
method Develops central limit theorems and consistent estimators for cross-validation.
result Provides asymptotically-exact confidence intervals and hypothesis tests.
bioLeak addresses data leakage in biomedical machine learning studies.
problem Data leakage causes optimistic bias in machine learning models for biomedical studies.
method bioLeak provides leakage-aware resampling workflows and model audits in R.
result The package supports various machine learning tasks and can detect leakage mechanisms.
Study compares mutation validation and cross-validation for model selection.
problem Comparing model selection methods for generalization performance and computational efficiency.
method Empirical comparison using benchmark and real-world datasets with Bayesian tests.
result Both methods select models with equivalent generalization performance but MV selects simpler models and is computationally cheaper.
Chiseling finds valid subgroups interactively, improving on existing methods.
problem Finding valid subgroups with inferential guarantees in regression and causal inference.
method Interactive subgroup refinement with inferential validity guarantees.
result Chiseling identifies better subgroups than existing methods with inferential guarantees.
New method uses interval-based metric to validate prediction uncertainty in machine learning.
problem Validation of prediction uncertainty in machine learning regression tasks is unreliable due to heavy-tailed distributions.
method Shift from variance-based metrics to interval-based Prediction Interval Coverage Probability (PICP).
result PICP method more quickly and reliably tests prediction intervals than variance-based metrics.
Paper offers anytime-valid inference for causal parameters using DML.
problem Classic DML is only valid asymptotically for a fixed sample size.
method Time-uniform DML results for anytime-valid inference.
result Valid inference at any arbitrary stopping time.
New method bounds hardware noise without assumptions.
problem Estimating hardware noise without assumptions.
method Machine Learning and Conformal Prediction.
result Theoretical upper bounds of fidelity.
A new method improves super learner validation efficiency.
problem Improving the efficiency of super learner validation.
method Bootstrap Bias Corrected Cross Validation applied to Super Learning.
result Bootstrap Bias Corrected Cross Validation proved efficient and cost-effective.
Improves full conformal prediction for stochastic non-conformity measures.
problem Inability of existing conditions to guarantee full conformal prediction validity under stochastic settings.
method Introduces a new sufficient condition: Conditional Independence & Permutation Invariance in Distribution.
result Corrects the insufficient condition and provides a new sufficient condition for full conformal prediction validity.
New approach uses interpolation models and error bounds for verifiable scientific machine learning.
problem Challenges in verifying and validating modern scientific machine learning workflows.
method Combines multiple standard interpolation techniques with error bounds for efficient computation and comparative performance analysis.
result Error bounds for interpolation techniques can be computed or estimated efficiently, aiding in validation goals.
The study uses machine learning to predict financial market trends.
problem Predicting financial market trends using low-frequency data.
method Modular online machine learning framework using stacked autoencoders and neural networks.
result The approach can predict financial market feature fluctuations effectively.
Improves statistical inference using machine learning predictions with imputed data.
problem Invalid statistical inference due to machine learning prediction errors.
method Bootstrap confidence intervals for nonuniform samples and arbitrary imputed features.
result Valid confidence intervals without assumptions on machine learning model quality.
Bagging stabilizes models without distributional assumptions.
problem Stability of machine learning models without distributional assumptions.
method Derives a finite-sample guarantee on bagging stability for any model.
result Guarantee applies to many bagging variants and is optimal.
Benchopt automates machine learning benchmarking across languages and hardware.
problem Limited transparency and tedious re-implementation work in machine learning validation.
method A collaborative framework for automating, reproducing, and publishing optimization benchmarks.
result Demonstrates practical findings that highlight the importance of details in machine learning validation.