Develops methods for valid and validated confidence sets in multiclass and multilabel prediction.
problem Challenges of typical conformal prediction methods in multiclass and multilabel problems, especially uneven coverage.
method Leverages quantile regression to build methods that always guarantee correct coverage and asymptotically optimal conditional coverage, addressing label interactions with tree-structured classifiers.
result Empirical evaluation suggests more robust coverage of confidence sets.
Improves test set performance and reduces out-of-sample disappointment for unstable models.
problem Ensuring strong test set performance via cross-validation for unstable models.
method Nested k-fold cross-validation with hyperparameter selection based on a weighted sum of cross-validation metric and model stability measure.
result Improves out-of-sample MSE for sparse ridge regression and CART by 4% and 2% respectively, compared to k-fold cross-validation.
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.
The paper offers guidelines for validating data-driven models.
problem Ensuring reliable validation of data-driven models.
method A set of general rules for model validation.
result Helps practitioners create reliable validation plans and report results transparently.
A new method controls risk for set predictors using cross-validation.
problem Inefficient set predictors when data limited.
method Cross-validation conformal risk control (CV-CRC).
result CV-CRC offers theoretical guarantees and reduces set size.
Mutation Validation method assesses model fit using mutated training labels without validation sets.
problem Model selection and hyperparameter tuning accuracy in supervised learning.
method Mutation Validation (MV) method using mutated training labels to assess model fit.
result MV provides more accurate model selection and stable hyperparameter tuning results.
Proposes a test to ensure predictive algorithms predict intended outcomes better than unintended ones.
problem Unintended model behavior leading to prediction of unintended outcomes.
method Falsification framework using nonparametric hypothesis testing to compare prediction losses across outcomes.
result Establishes discriminant validity with respect to gender but not race in an admissions setting.
A new method selects training samples for fine-tuning using validation set inference.
problem Selecting training examples for fine-tuning with limited target data.
method Invert train-validation roles; select samples affecting most predictions.
result Our method achieves lower test log-loss than state-of-the-art approaches.
Proposes a falsification framework to test algorithmic discriminant validity.
problem Unintended model behavior in predictive algorithms.
method Falsification framework based on statistical tests comparing prediction losses across outcomes.
result Establishes discriminant validity for some outcomes but not others.
We compare and contrast two approaches to validating a trained classifier while using all in-sample data for training. One is simultaneous validation over an organized set of hypotheses (SVOOSH), the well-known method that began with VC theory. The other is withhold and gap (WAG). WAG withholds a validation set, trains…
Develops CPL for optimal prediction set length and validity.
problem Balancing conditional validity and length efficiency in conformal prediction.
method Conformal Prediction with Length-Optimization (CPL).
result Achieves optimal prediction set length while maintaining conditional validity.
Method selects valid IVs from a large set using clustering and test of overidentifying restrictions.
problem Selecting valid instrumental variables from a large set of candidates.
method Agglomerative hierarchical clustering combined with a test of overidentifying restrictions.
result Achieves oracle properties when the largest group of IVs is valid.
Proposes a new cross-validation method to estimate model performance.
problem The standard cross-validation method does not accurately estimate the performance of the recommended model.
method Develops a new random-effects model framework to improve naive cross-validation estimators.
result Proposed estimators outperform conventional and naive methods in estimating model performance.
Optimizes Lasso hyperparameters using leave-one-out CV.
problem Finding optimal hyperparameters for Lasso regression.
method Develops an algorithm to compute exact or approximate leave-one-out CV.
result Algorithm finds optimal hyperparameters for Lasso.
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.
A method to learn from noisy labels without a clean validation set.
problem Learning from samples with noisy labels.
method Limited Gradient Descent: modifying labels to estimate optimal stopping timing.
result Comparable and sometimes superior generalization performance compared to methods relying on clean validation sets.
This work trains a model to generate all valid commands for text-based games.
problem Generating valid commands for text-based games.
method Training generative models on a dataset of text-based game contexts.
result The best model can generate valid commands unseen at training and achieves high F1 score.
Extends machine learning model training to include validation data.
problem Machine learning validation data usage in training.
method Extends predictive information bottleneck to include validation data.
result Validation data improves model training efficiency.
With the increasing size of today's data sets, finding the right parameter configuration in model selection via cross-validation can be an extremely time-consuming task. In this paper we propose an improved cross-validation procedure which uses nonparametric testing coupled with sequential analysis to determine the bes…
The paper extends conformal risk control to be valid with high probability over a growing calibration dataset.
problem Valid risk control over a growing calibration dataset.
method Quantile-based arguments for anytime-valid control.
result Guarantees remain valid with high probability over a cumulatively growing calibration dataset.
Early stopping is a widely used technique to prevent poor generalization performance when training an over-expressive model by means of gradient-based optimization. To find a good point to halt the optimizer, a common practice is to split the dataset into a training and a smaller validation set to obtain an ongoing est…
Linear principal component analysis (PCA) can be extended to a nonlinear PCA by using artificial neural networks. But the benefit of curved components requires a careful control of the model complexity. Moreover, standard techniques for model selection, including cross-validation and more generally the use of an indepe…
Valid prediction sets for dynamic graphs using conformal prediction.
problem Uncertainty quantification in dynamic graph neural networks.
method Dynamic graph unfolding for input to GNNs, combined with conformal prediction.
result Valid prediction sets with minimal assumptions, even in challenging scenarios.
We present a novel regularization approach to train neural networks that enjoys better generalization and test error than standard stochastic gradient descent. Our approach is based on the principles of cross-validation, where a validation set is used to limit the model overfitting. We formulate such principles as a bi…
New framework validates counterfactual estimations in network interference settings.
problem Challenges in causal effect estimation and validation in network interference settings.
method Introduces a distribution-preserving network bootstrap and counterfactual cross-validation procedure.
result Validates counterfactual estimations in diverse network interference settings.
Due to the increasing availability of high-dimensional empirical applications in many research disciplines, valid simultaneous inference becomes more and more important. For instance, high-dimensional settings might arise in economic studies due to very rich data sets with many potential covariates or in the analysis o…
Cross-validation is one of the most popular model selection methods in statistics and machine learning. Despite its wide applicability, traditional cross validation methods tend to select overfitting models, due to the ignorance of the uncertainty in the testing sample. We develop a new, statistically principled infere…
Generalizes conformal prediction to multiple learnable parameters for efficient prediction sets.
problem Learning valid and efficient prediction sets with low-capacity function classes.
method Constrained empirical risk minimization (ERM) with gradient-based optimization of differentiable surrogate losses and Lagrangians.
result Achieves approximate valid population coverage and near-optimal efficiency within class.
Enhances clustering quality evaluation in noisy data.
problem Reliable clustering quality assessment in noisy Gaussian mixtures.
method Feature Importance Rescaling (FIR) method.
result FIR improves correlation between cluster validity indices and ground truth.
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.
Valid causal inference with unobserved confounding in high-dimensional settings.
problem Estimating causal effects with unobserved confounders in high-dimensional data.
method Proposes methods to estimate causal effects with valid confidence intervals in the presence of unobserved confounders and high-dimensional nuisance models.
result Valid semiparametric inference can be obtained with unobserved confounding, and uncertainty intervals are proposed.
Cluster analysis is used to explore structure in unlabeled data sets in a wide range of applications. An important part of cluster analysis is validating the quality of computationally obtained clusters. A large number of different internal indices have been developed for validation in the offline setting. However, thi…
This paper identifies a problem with the usual procedure for L2-regularization parameter estimation in a domain adaptation setting. In such a setting, there are differences between the distributions generating the training data (source domain) and the test data (target domain). The usual cross-validation procedure requ…
CPTD improves prediction intervals in time series regression with cross-sectional data.
problem Constructing valid prediction intervals in time series regression with a cross-section.
method Conformal Prediction with Temporal Dependence (CPTD) for post-hoc, light-weight approach.
result CPTD maintains cross-sectional validity while improving longitudinal coverage.
Optimizes minimum-volume prediction sets for multivariate regression.
problem Lack of efficient methods for multivariate conformal prediction.
method Optimization-driven framework for minimum-volume covering sets.
result Efficient and informative prediction sets with tight coverage.
Paper revisits pre-validation method, improving hypothesis testing.
problem Improving hypothesis testing in pre-validated models with different feature dimensions.
method Extended problem formulation, analytical distribution, and bootstrap procedure.
result Proposed analytical distribution and bootstrap procedure for pre-validated predictors.
Four geometries govern sequential and distribution-free inference.
problem Sequential and distribution-free inference challenges.
method Four distinct admissibility geometries.
result Four classes of admissible procedures are pairwise non-nested.
In this article, we derive concentration inequalities for the cross-validation estimate of the generalization error for subagged estimators, both for classification and regressor. General loss functions and class of predictors with both finite and infinite VC-dimension are considered. We slightly generalize the formali…
Valid p-value for bounded random variables without distributional assumptions.
problem Calibration of predictive algorithms in a distribution-free setting.
method Built a super-uniform p-value based on a concentration inequality.
result Super-uniform p-value is tighter than existing alternatives.
A stability-based method selects the most desirable conformal prediction set.
problem Selecting the most desirable conformal prediction set from multiple valid sets invalidates coverage guarantees.
method A stability-based approach that ensures coverage for the selected prediction set.
result The stability-based approach maintains coverage guarantees for the selected prediction set.
Paper introduces methods to adjust for missing data in causal inference.
problem Missing data and selection bias in causal inference.
method Developed necessary and sufficient conditions for valid adjustment sets.
result Introduced algorithms for finding minimum adjustment sets.
New method infers causal effects without knowing control variables.
problem Inference errors when control variables are unknown.
method Proposes a method for inferring causal effects when control variables are unknown.
result Proves method yields asymptotically valid confidence intervals for average causal effects.
Bayesian inference corrected for bias in high-dimensional models.
problem Bayesian inference for high-dimensional regression models often produces biased credible sets.
method Debiasing approach based on Bernstein-von Mises theorem.
result Frequentist validity of debiased Bayesian posterior.
We consider the parametric learning problem, where the objective of the learner is determined by a parametric loss function. Employing empirical risk minimization with possibly regularization, the inferred parameter vector will be biased toward the training samples. Such bias is measured by the cross validation procedu…
In this article, we derive concentration inequalities for the cross-validation estimate of the generalization error for empirical risk minimizers. In the general setting, we prove sanity-check bounds in the spirit of \cite{KR99} \textquotedblleft\textit{bounds showing that the worst-case error of this estimate is not m…
Model selection on validation data is an essential step in machine learning. While the mixing of data between training and validation is considered taboo, practitioners often violate it to increase performance. Here, we offer a simple, practical method for using the validation set for training, which allows for a conti…
New IF method improves accuracy in deep neural networks with noisy data.
problem Inaccurate influence estimates in deep neural networks, especially with noisy data.
method Established a connection between influence estimation error, validation set risk, and sharpness, introducing a novel estimation form for flat validation minima.
result Our novel Influence Function approach provides more accurate influence estimates, validated across various tasks.
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.