The paper improves the robustness of approximate randomization tests.
problem Noisy data limits the robustness of approximate randomization tests.
method Derives non-asymptotic bounds and novel conditions for approximate randomization tests.
result Valid approximate randomization tests under data invariances can be derived.
BERET improves binary expansion test for multivariate independence.
problem Testing independence of random vectors in arbitrary dimensions.
method Ensemble approach using sum of squared symmetry statistics and distance correlation.
result Improves power while preserving interpretability.
New method combines randomization tests and flexible models for valid inference without splitting data.
problem Valid inference in randomized panel experiments with complex effect heterogeneity.
method Model-assisted randomization tests that estimate unsigned CATE from residualized outcomes.
result CATE-assisted tests control Type I error and achieve higher power than alternatives.
Develops efficient nonparametric testing with random projections.
problem High computational complexity in nonparametric inference with large data.
method Random projection strategy for kernel ridge regression.
result Achieves testing optimality with minimum number of projections.
Paper studies statistical tests on infinite random graphs.
problem Testing hypotheses on infinite random graphs.
method Formalism for stationarity, generalized time series results.
result Criterion for consistent test existence.
Improved MMD test for two-sample testing with random Fourier features.
problem Quadratic-time complexity of MMD test for large-scale analysis.
method Approximated MMD test using random Fourier features, investigating time-power trade-off.
result Sub-quadratic time complexity with same minimax separation rates as MMD test.
Two new tests approximate KCIT for fast CI testing in large datasets.
problem CI testing is slow and resource-intensive for large datasets.
method Developed RCIT and RCoT, which approximate KCIT using random Fourier features.
result RCIT and RCoT scale linearly with sample size and return accurate p-values faster than KCIT.
Develops tests for conditional symmetry under group actions.
problem Testing conditional symmetry in distributions under group actions.
method Nonparametric randomization tests with kernel methods and asymptotic consistency.
result Tests achieve finite-sample Type I error control and power.
New test detects sparse alternatives in Gaussian random fields.
problem Detecting sparse alternatives in Gaussian random fields.
method Ad-hoc Kac Rice formula for second maximum distribution, exact spacing test.
result Exact t-spacing test for high power in detecting sparse alternatives. A new test for IRG models using KSD for small networks.
problem Testing goodness-of-fit for inhomogeneous random graph models.
method Kernelised Stein Discrepancy (KSD) test for IRG models.
result The test is effective for small networks and provides theoretical guarantees.
This study examines how financial tick data becomes more random with time aggregation.
problem Investigating the randomness of financial tick data over time.
method Applied statistical randomness tests from NIST and TestU01 batteries to ultra-high frequency financial data.
result Financial tick data becomes increasingly random as the aggregation level of transaction time increases.
MULTIFIT tests independence between two random vectors using multiscale Fisher's test.
problem Detecting local dependence between two random vectors.
method MULTIFIT uses a resampling-free approach to test independence.
result MULTIFIT can easily handle large sample sizes and interpret dependency nature.
A new testing method for random forests scales well for big data.
problem Efficiently assessing feature significance in random forests.
method Permutation-style testing approach, leveraging exchangeability arguments.
result The test maintains high power with significantly fewer computations.
A new non parametric approach to the problem of testing the independence of two random process is developed. The test statistic is the Hilbert Schmidt Independence Criterion (HSIC), which was used previously in testing independence for i.i.d pairs of variables. The asymptotic behaviour of HSIC is established when compu…
Detects dense subhypergraphs in heterogeneous random hypergraphs.
problem Testing for the existence of a dense subhypergraph in heterogeneous random hypergraphs.
method Established detection boundaries and constructed asymptotically powerful and adaptive tests.
result Developed tests for distinguishing between null and alternative hypotheses.
New method improves feature importance assessment in random forests.
problem Improving feature importance measures for random forests.
method Hypothesis testing via self-normalized feature-residual correlation test (FACT).
result The method provides theoretically justified feature importance tests with controlled type I error and appealing power.
Study loop corrections in random feature models affecting training and test errors.
problem Analyzing loop corrections in random feature models to understand training and test errors.
method Statistical physics and effective field theory approach to study loop corrections.
result Derived loop corrections to training error, test error, and generalization gap.
The paper explains how many random seeds are needed for statistical significance in deep reinforcement learning experiments.
problem Ensuring statistical significance in deep reinforcement learning experiments.
method Theoretical guidelines for determining the number of random seeds for t-tests and bootstrap confidence intervals.
result Deviations from statistical test assumptions can lead to inaccurate evaluations of statistical errors.
A new test controls type 1 error and has good power for online experiments.
problem Testing complex metrics and preventing type 1 error inflation in online randomized experiments.
method Nonparametric sequential test using bootstrap and mixture SPT.
result The test controls type 1 error and has good power in online experiments.
Paper improves power of conditional randomization tests.
problem Improving power of conditional randomization tests.
method Introducing a new cost function to maximize test statistic power.
result Consistently increases the number of correct discoveries.
A new method uses randomized trials to estimate the strength of unobserved confounding.
problem Unobserved confounding compromises causal conclusions from non-randomized studies.
method Designs a statistical test to detect unobserved confounding strength and estimates a lower bound.
result Estimates an asymptotically valid lower bound on unobserved confounding strength.
Optimal distributed testing under communication constraints with shared randomness.
problem Signal detection in a distributed system with limited communication.
method Derivation of minimax testing errors, distributed testing algorithms, and theoretical lower bounds.
result Consistent nonparametric distributed testing is possible even with minimal communication.
Paper uses ML to improve A/B testing for complex treatment effects.
problem Detecting treatment effects in A/B experiments with complex variables.
method Combines ML models with randomization tests for better detection of treatment effects.
result ML-assisted tests improve detection of complex treatment effects.
The paper reviews methods for testing randomness and exchangeability in sequential data.
problem Testing the randomness and exchangeability of sequential data.
method Conformal martingales for online testing of randomness and exchangeability.
result Valid and efficiency results for various conformal martingale-based procedures.
DPE embeds non-Euclidean objects into Hilbert space for independence testing.
problem Testing independence of non-Euclidean random objects.
method Distance Profile Embedding (DPE) maps objects into Hilbert space.
result Unified framework for marginal and conditional independence testing.
Study uses random matrix test to find significant factors in cryptocurrency forecasts.
problem Determining the optimal number of factors in cryptocurrency forecast models.
method Applied a random matrix test to a forecast model of Reduced Rank Regression (RRR) on cryptocurrencies.
result Consistent results with visual inspection, minimal computational cost compared to cross-validation.
Single tree outperforms random forest in testing accuracy.
problem The challenge of improving single decision tree performance.
method Gradient-based entire tree optimization framework, scaled sigmoid approximation, numerical stability algorithm, subtree polish strategy.
result Optimized single tree outperforms classic random forest by 2.03% on average.
New bounds found for minimum tests needed in group testing.
problem Determining the minimum number of tests to detect defective items.
method Analyzing non-adaptive randomized algorithms for various group testing models.
result Tight bounds for the minimum number of tests and their limits.
A test for comparing large random graphs based on network statistics.
problem Comparing friendship networks on Facebook and LinkedIn.
method General principle for two-sample hypothesis testing based on concentration of network statistics.
result A consistent two-sample test that is minimax optimal for certain network statistics.
Study tests financial market efficiency using random number generator tests.
problem Check for informational efficiencies in financial markets.
method Analysed binary daily returns as random number generators, split analysis by annual and company levels, investigated longer-term efficiency over Nasdaq-listed companies.
result Information efficiency varies across years and reflects large-scale market impacts.
Study evaluates RKHS choices for assessing graph models using KSD tests.
problem Effect of RKHS choice on KSD tests for graph model assessment.
method Investigated power performance and computational runtime of KSD tests for ERGMs and synthetic graph generators.
result Different RKHS choices affect KSD test performance and computational runtime.
While statistical learning methods have proved powerful tools for predictive modeling, the black-box nature of the models they produce can severely limit their interpretability and the ability to conduct formal inference. However, the natural structure of ensemble learners like bagged trees and random forests has been …
Bayes-optimal learning of deep random networks with Gaussian weights is studied.
problem Learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights.
method Closed-form expressions for Bayes-optimal test error, ridge regression, kernel and random features regression are computed.
result Optimally regularized ridge regression and kernel regression achieve Bayes-optimal performances, while logistic loss yields a near-optimal test error for classification.
Power of network tests degrades when vertices are misaligned.
problem Power loss in network hypothesis testing due to vertex shuffling.
method Theoretical analysis and simulations of Frobenius norm differences in random dot product and stochastic block models.
result Shuffling vertices can significantly reduce the power of network tests.
New measures quantify mutual dependence between multiple random vectors.
problem Measuring mutual dependence between multiple random vectors.
method Proposes three measures based on generalized distance covariance.
result Empirical and simplified empirical measures effectively test mutual independence.
Generative adversarial networks improve pseudo-random number generation.
problem Improving the quality of pseudo-random number generators.
method Training a GAN to generate sequences that are hard for an adversary to predict.
result GAN-trained neural networks can produce pseudo-random sequences with good statistical properties.
Optimal AFs minimize RFR test error and sensitivity.
problem Finding optimal AFs for RFR to minimize test error and sensitivity.
method Closed-form solution for AFs minimizing test error and sensitivity under different functional parsimony.
result Optimal AFs can be linear, saturated linear, or Hermite polynomial expressions.
Tests if vertices in graphs have the same latent positions.
problem Testing equality of latent positions in random graphs.
method Empirical Mahalanobis distances from spectral embeddings.
result Test statistics follow chi-square distributions under null and local alternatives.
New framework minimizes interference and selection bias in network A/B testing.
problem Interference and selection bias in network A/B testing.
method Proposes a principled framework that jointly minimizes interference and selection bias using edge spillover probability and cluster matching.
result Significantly lower error in causal effect estimation compared to existing solutions.
DIET tests conditional independence using marginal dependence measures of residual information.
problem Computational intractability of conditional randomization tests (CRTs).
method DIET avoids fitting large models by leveraging marginal independence statistics of information residuals.
result DIET achieves higher power than other tractable CRTs on synthetic and real benchmarks.
A new test assesses how well observed networks fit a specified ERGM model.
problem Testing the goodness of fit for ERGMs with a single network observation.
method Kernel Stein discrepancy combined with a discrete Stein operator for ERGMs, Monte Carlo simulation.
result The test provides theoretical and practical support for assessing ERGM fit.
A new method reduces computational costs for testing RF variable importance measures.
problem Testing variable importance measures from random forests is computationally expensive and challenging.
method Sequential permutation testing and sequential p-value estimation to reduce computational costs.
result Theoretical properties of sequential tests are confirmed, maintaining type-I error and high power.
Paper uses Random Matrix Theory for optimal training-testing data split.
problem Finding ideal training-testing data split for linear regression.
method Random Matrix Theory applied to Gaussian multivariate data.
result Ideal training and test sizes derived for any model.
CovRegRF estimates covariance matrix from covariates using random forests.
problem Estimating conditional covariances or correlations among multivariate responses.
method Random forest trees with a custom splitting rule to maximize covariance difference.
result Accurate covariance matrix estimates and controlled Type-1 error.
Study evaluates neural networks based on random graph structures and finds key performance indicators.
problem Understanding and optimizing neural network architectures using graph theory.
method Evaluation of neural networks with random graph structures, focusing on structural and numerical properties.
result A new numerical graph characteristic selects a set of quasi-1-dimensional graphs that perform well.
A new test for comparing distributions is proposed, balancing optimality and efficiency.
problem Comparing distributions defined over non-Euclidean domains.
method Spectral-regularized two-sample test based on random Fourier features.
result The proposed test is minimax optimal under certain conditions.
We find a deterministic equivalent for random feature regression's test error, independent of feature map dimension.
problem Understanding the generalization performance of random feature ridge regression.
method We derive a deterministic equivalent for the test error of RFRR under a concentration property, showing it can be approximated by a closed-form expression dependent on feature map eigenvalues.
result Our approximation guarantee is non-asymptotic, multiplicative, and independent of the feature map dimension, providing a tight result for the smallest number of features achieving optimal minimax error rate.
Test-wise deletion improves causal inference by saving more samples than list-wise deletion.
problem Missing not at random (MNAR) data in causal inference.
method Test-wise deletion of samples only among variables required for each CI test.
result FCI and RFCI with test-wise deletion outperform other methods on average.