A new method for kernel tests without data splitting increases power.
problem Lack of power in kernel-based tests due to data splitting.
method Selective inference framework to learn hyperparameters and test on full sample.
result Empirically larger test power without data splitting, regardless of split proportion.
MaxRR efficiently unlearns models by splitting and selecting core samples.
problem Efficiently unlearning models while verifying unlearning guarantees.
method Model splitting and core sample selection with a generalized unlearning metric.
result MaxRR achieves efficient unlearning with properties matching full retraining.
A method to split a data point into two parts that individually cannot reconstruct the whole, but together can.
problem Splitting a single data point into two parts such that neither can reconstruct the whole but together can.
method Borrowing ideas from Bayesian inference to achieve a continuous analog of data splitting.
result A method to achieve data fission, enabling post-selection inference in finite samples.
The paper explores how splitting data samples influences optimal neural network hyperparameters.
problem Understanding the effectiveness of neural networks and their hyperparameters.
method Investigates the role of sample splitting in neural network hyperparameter selection.
result Optimal hyperparameters derived from sample splitting lead to a neural network model that minimizes prediction risk asymptotically.
Improves decision tree performance by correcting split selection errors.
problem Invalid statistical guarantees in split selection for decision trees.
method Introduces anytime-valid inference to provide valid statistical guarantees.
result Provides anytime-valid control of false splits under arbitrary data streams.
Novel methods for splitting Gaussian mixtures improve uncertainty propagation in nonlinear systems.
problem Improving accuracy and efficiency in nonlinear uncertainty propagation.
method Preserving mean and covariance, novel heuristics for selecting splitting direction informed by initial uncertainty and nonlinear function properties.
result Improved accuracy and efficiency in uncertainty propagation compared to existing techniques.
OptCS optimizes model selection after conformal inference, controlling FDR and power loss.
problem Challenges in model selection for conformal inference, especially when limited labeled data and many model choices are available.
method OptCS framework that allows valid statistical testing after flexible data-driven model optimization, using novel multiple testing procedures.
result Valid conformal p-values constructed despite substantial data reuse, maintaining FDR control.
New method selects best HTE estimator without ground-truth treatment effects.
problem Selecting best HTE estimator from multiple candidates.
method Cross-fitted, exponentially weighted test statistic with two-way sample splitting.
result Empirically, reliable error control and reduced false selections.
The study examines stock splits and their effects on companies, managers, and shareholders.
problem Misunderstandings and confounding factors around stock splits and their impacts.
method Selected database analysis of nine recent events, examining market impact, trading volume, and shareholder base.
result Stock splits enhance trading volume, increase shareholder base, and improve market liquidity.
Optimizes data splitting for shorter conformal prediction intervals.
problem Minimizing prediction interval length while maintaining coverage.
method Theoretical framework for optimal data splitting in split conformal prediction.
result Analytical characterizations of length-optimal split ratios in various settings.
The paper introduces a new model to correct bias in treatment effect estimates due to sample selection.
problem Bias in treatment effect estimates due to sample selection.
method Type 2 Tobit Bayesian Additive Regression Trees (TOBART-2) with Dirichlet Process Mixture distribution and soft trees.
result Corrects bias in treatment effect estimates by accounting for nonlinearities and model uncertainty.
We propose a new algorithm called PLUTO for building logistic regression trees to binary response data. PLUTO can capture the nonlinear and interaction patterns in messy data by recursively partitioning the sample space. It fits a simple or a multiple linear logistic regression model in each partition. PLUTO employs th…
In the regression setting, given a set of hyper-parameters, a model-estimation procedure constructs a model from training data. The optimal hyper-parameters that minimize generalization error of the model are usually unknown. In practice they are often estimated using split-sample validation. Up to now, there is an ope…
While many statistical models and methods are now available for network analysis, resampling network data remains a challenging problem. Cross-validation is a useful general tool for model selection and parameter tuning, but is not directly applicable to networks since splitting network nodes into groups requires delet…
The most popular approach for analyzing survival data is the Cox regression model. The Cox model may, however, be misspecified, and its proportionality assumption may not always be fulfilled. An alternative approach for survival prediction is random forests for survival outcomes. The standard split criterion for random…
Causal trees struggle with accuracy in estimating treatment effects.
problem Estimating heterogeneous causal treatment effects using recursive decision trees.
method Adaptive recursive partitioning with and without sample splitting.
result Causal tree estimators can have uniform-norm errors decreasing more slowly than any power of the sample size.
Random forest hyperparameters affect variable selection in omics studies.
problem Impact of hyperparameters on variable selection in random forests.
method Two simulation studies using theoretical and empirical data.
result Hyperparameters influence variable selection more than the splitting strategy and sample fraction.
New method splits unknown covariance Gaussians into independent parts.
problem Splitting multivariate Gaussian data with unknown covariance.
method Developed a general algorithm for decomposing unknown covariance Gaussians.
result Demonstrated decomposition for single multivariate Gaussian with unknown covariance.
Develops a prediction method based on sampling design.
problem Creating accurate individual predictions.
method Design-based approach using expected cross-validation results.
result Valid inference of unobserved prediction errors defined with respect to sampling design.
The paper develops methods to estimate treatment effects in sample selection models.
problem Evaluation of treatments when outcomes are only observed for a subpopulation due to sample selection or attrition.
method Combines selection-on-observables and instrumental variable assumptions with double machine learning for treatment evaluation.
result Proposed estimators are asymptotically normal and root-n consistent.
A new method for causal inference in high-dimensional data using machine learning.
problem Causal inference in high-dimensional observational data.
method Support Points Sample Splitting (SPSS) for efficient double machine learning (DML) in causal inference.
result Deep learning with SPSS and hybrid methods outperform SVM with SPSS in computational efficiency and estimation quality.
TA-CQR predicts regression intervals with exact coverage, splitting miscoverage between endpoints.
problem Predicting regression intervals with exact coverage under reporting constraints.
method TA-CQR uses tail allocation to parameterize the oracle, estimating the allocation by searching quantile cores and applying nonnegative additive split-conformal calibration.
result TA-CQR achieves exact finite-sample marginal coverage under exchangeability, with theoretical guarantees on calibration and length.
Data thinning splits observations into independent parts for convolution-closed distributions.
problem Validation of unsupervised learning results in settings with limited data.
method Data thinning, splitting observations into independent parts following the same distribution.
result Data thinning provides an attractive alternative to cross-validation in settings with limited sample splitting.
CIT and CIF improve feature selection for downstream prediction.
problem Feature selection bias in machine learning models.
method Conditional inference trees and forests with Bonferroni correction.
result CIF ranks top 3 among 18 regression methods and top 4 among 17 classification methods.
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…
A new MMD-based test combines kernels for two-sample testing without splitting data.
problem Efficiently testing if two datasets come from the same distribution without splitting data.
method Proposes a novel statistic based on Maximum Mean Discrepancy (MMD) that combines kernels, proving concentration bounds and showing data-dependent kernel selection.
result Exponential concentration bounds and improved test power compared to existing methods.
This paper presents the asymptotic behavior of a linear instrumental variables (IV) estimator that uses a ridge regression penalty. The regularization tuning parameter is selected empirically by splitting the observed data into training and test samples. Conditional on the tuning parameter, the training sample creates …
FoLDTree improves oblique decision trees with ULDA, enhancing accuracy and feature selection.
problem Axis-orthogonal splits limit traditional decision trees' performance on oblique decision boundaries.
method Integrates ULDA into decision tree structure for efficient oblique splits, feature selection, and handling missing values.
result FoLDTree outperforms other methods in accuracy and feature selection, comparable to random forest.
A hybrid algorithm fuses significance-based splitting with honest sample-splitting for estimating heterogeneous treatment effects.
problem Estimating heterogeneous treatment effects while maintaining valid inference.
method Significance-first splitting using a squared t-statistic for treatment imes side interaction. result Achieves approximately 90% CI coverage at the 90% nominal level across various synthetic designs and datasets.
Paper develops a new method for open-set and imbalanced classification with valid prediction sets.
problem Tackles open-set and imbalanced classification with new prediction methods.
method Develops a new family of conformal p-values and a selective sample splitting algorithm.
result Valid prediction sets with valid coverage in open-set scenarios and informative predictions under extreme class imbalance.
Decision tree classifiers are a widely used tool in data stream mining. The use of confidence intervals to estimate the gain associated with each split leads to very effective methods, like the popular Hoeffding tree algorithm. From a statistical viewpoint, the analysis of decision tree classifiers in a streaming setti…
This work analyzes tree-based methods from a ranking perspective, providing insights and new statistics.
problem Understanding the effectiveness of tree-based methods in finite-sample settings, especially symbolic feature selection.
method Local ranking perspective, finite-sample analysis, oracle bounds, posterior contraction results, concordant divergence statistics.
result New insights and statistics for evaluating symbolic feature mappings.
A method for non-parametric conditional distribution estimation using CRPS-optimal binning.
problem Non-parametric conditional distribution estimation.
method Partitioning covariate-sorted observations into bins to minimize LOO-CRPS, selecting K by K-fold cross-validation of test CRPS.
result Produces narrower prediction intervals with near-nominal coverage compared to split-conformal competitors.
This study analyzes prediction risk for PCR method in latent factor regression models.
problem Prediction risk analysis in latent factor regression models.
method Adaptive PCR method with risk bounds established under factor regression model.
result Unified framework for analyzing various linear prediction methods under factor regression.
Though black-box predictors are state-of-the-art for many complex tasks, they often fail to properly quantify predictive uncertainty and may provide inappropriate predictions for unfamiliar data. Instead, we can learn more reliable models by letting them either output a prediction set or abstain when the uncertainty is…
A new test statistic speeds up MMD while maintaining power.
problem Efficiently testing two distributions without permutations.
method Cross-MMD statistic based on sample-splitting and studentization.
result Cross-MMD has a limiting standard Gaussian distribution under the null.
Study on estimating causal effects with limited data and multiple environments.
problem Estimating causal effects under hidden confounding with unpaired data and sparse effects.
method Instrumental variable (IV) regression with cross-fold sample splitting and ℓ1-regularized estimation. result Proposed GMM-type estimator is consistent as the number of environments grows.
Approach selects variables and time intervals for comparing high-dimensional time-series data.
problem Comparing high-dimensional time-series data for significant differences.
method Data is split into subintervals, and two-sample tests are performed on each to identify distinguishing variables.
result The approach effectively identifies variables and time intervals where data significantly differs.
Recursive partitioning approaches producing tree-like models are a long standing staple of predictive modeling, in the last decade mostly as ``sub-learners'' within state of the art ensemble methods like Boosting and Random Forest. However, a fundamental flaw in the partitioning (or splitting) rule of commonly used tre…
Assigning significance in high-dimensional regression is challenging. Most computationally efficient selection algorithms cannot guard against inclusion of noise variables. Asymptotically valid p-values are not available. An exception is a recent proposal by Wasserman and Roeder (2008) which splits the data into two pa…
Optimal tuning for estimating ECC in proportional asymptotics.
problem Estimating Expected Conditional Covariance (ECC) under proportional asymptotics.
method Debiased ridge regression estimators for nuisance functions, sample splitting strategies, and asymptotic variance analysis.
result Prediction-optimal tuning parameters may not minimize asymptotic variance of ECC estimator.
Optimal sparse recovery with decision stumps achieves strong feature selection guarantees.
problem Sparse recovery of active features from high-dimensional data.
method Analysis of single-depth decision trees (decision stumps) for feature selection in linear regression.
result Tight sample performance guarantees for O(slogp), improving upon previous bounds. Proposes a method to compute valid lower confidence bounds for multiple models selected based on their performance.
problem Model selection and evaluation in machine learning.
method Interprets model selection as a simultaneous inference problem, uses bootstrap tilting and maxT-type multiplicity correction.
result Yields valid lower confidence bounds that are at least as good as standard approaches and reliably reach nominal coverage probability.
A machine learning configuration refers to a combination of preprocessor, learner, and hyperparameters. Given a set of configurations and a large dataset randomly split into training and testing set, we study how to efficiently select the best configuration with approximately the highest testing accuracy when trained f…
A new method speeds up sampling in diffusion models.
problem Slow sample generation in diffusion models.
method Proposed Splitting Integrators for fast stochastic sampling.
result Achieved FID score of 2.36 in 100 NFE, significantly faster than baselines.
Develops a new inference method for split-sample estimators using multiple splits.
problem Statistical dependence and variability in split-sample estimators.
method Averaging across multiple splits, proving a central limit theorem, and developing new inference approaches.
result Valid confidence intervals and improved power in comparing model performance.
We propose a tree regularization framework, which enables many tree models to perform feature selection efficiently. The key idea of the regularization framework is to penalize selecting a new feature for splitting when its gain (e.g. information gain) is similar to the features used in previous splits. The regularizat…
Study examines inference methods after variable selection in Cox models.
problem Bias and misleading inference after variable selection in Cox models.
method Simulation study of inference procedures for Lasso and adaptive Lasso in Cox models.
result Performance of inference procedures varies, with debiased Lasso showing promise.