New test statistics improve independence testing in high dimensions.
problem Testing independence in high-dimensional data.
method Derive joint limiting laws for extreme-value and quadratic form statistics.
result Joint limiting laws of extreme-value and quadratic form statistics are asymptotically independent.
Empirical study of leading measures of dependence for data analysis.
problem Identifying promising pairwise associations in data analysis.
method Extensive empirical evaluation of equitability, power against independence, and runtime of several measures of dependence.
result MICe is most equitable on functional relationships, while TICe is state-of-the-art in power against independence.
The paper analyzes the power of MX CI tests and finds likelihood-based statistics most powerful.
problem Testing conditional independence under model-X assumptions.
method Conditional randomization test (CRT) and MX knockoffs.
result Likelihood-based statistics are most powerful in MX CI tests.
New method tests causal association using noise contrastive backdoor adjustment.
problem Testing causal association in complex settings with many confounders.
method Backdoor-HSIC (bd-HSIC) using HSIC for independence testing.
result Calibrated and powerful for binary and continuous treatments with many confounders.
Sequential tests for two-sample and independence testing using betting strategies.
problem Testing sequential data for two-sample and independence without kernel selection issues.
method Prediction-based betting strategies that adaptively determine distribution and joint distribution.
result Prediction-based tests outperform kernel-based approaches in high-dimensional or structured data settings.
Deep-learning method improves hypothesis testing for independence.
problem Improving hypothesis testing for independence using deep learning.
method Proposes deep-testing, a novel procedure that uses a deep neural network to distinguish between data generated under and outside a given statistical model.
result Deep-testing achieves the highest overall power against nineteen competing methods across various dependence structures.
We introduce kernel nonparametric tests for Lancaster three-variable interaction and for total independence, using embeddings of signed measures into a reproducing kernel Hilbert space. The resulting test statistics are straightforward to compute, and are used in powerful interaction tests, which are consistent against…
optHSIC tests independence between covariates and censored lifetimes using optimal transport.
problem Testing independence between a covariate and right-censored lifetimes.
method optHSIC uses optimal transport to transform censored data into uncensored data, then applies a permutation test with a kernel-based dependence measure.
result optHSIC has power against a wider class of alternatives than Cox regression and maintains type 1 error control even when censoring depends on the covariate.
Study shows optimal rates for independence testing via U-statistic permutation tests.
problem Developing a valid test of independence for pairs with additional smoothness constraints.
method Defining a measure of dependence, using a permutation test based on a basis expansion and U-statistic estimator.
result Proves minimax optimality of the test in separation rates for certain cases.
A new kernel test avoids permutations for independence testing.
problem Intractable null distributions of kernel statistics.
method Developed xHSIC and xdCov, avoiding permutations.
result New tests have limiting Gaussian distributions under null.
This paper is about two related decision theoretic problems, nonparametric two-sample testing and independence testing. There is a belief that two recently proposed solutions, based on kernels and distances between pairs of points, behave well in high-dimensional settings. We identify different sources of misconception…
New method tests CMI using deep neural networks for high-dimensional data.
problem Testing conditional mean independence in high-dimensional settings.
method Population CMI measure and bootstrap-based testing with deep generative neural networks.
result Strong empirical performance and versatility in various scenarios.
A new test method improves goodness-of-fit tests for copulas.
problem Developing robust tests for copula goodness-of-fit.
method Binary Expansion Approximation of UniformiTY (BEAUTY) and Binary Expansion Adaptive Symmetry Test (BEAST).
result The BEAST method improves empirical power against various alternatives.
This paper shows how to construct sequential tests with power one against weakly compact sets in Polish spaces.
problem Testing composite null hypotheses involving weakly compact sets in Polish spaces.
method Develops sequential tests for i.i.d. laws in Polish spaces, providing a sufficient condition for power one.
result Power-one sequential tests exist for weakly compact sets against their complements in i.i.d. laws in Polish spaces.
New model improves GP approximations by relaxing independence across resolutions.
problem Overfitting and non-smooth predictions in multiresolution GPs.
method Conditional independence among GPs across resolutions.
result Improved robustness against overfitting and smoother predictions.
Framework for online hypothesis testing across various data types.
problem Testing various nonparametric hypotheses in data streams.
method Unified framework using operators on data distributions, leveraging ML models.
result Efficient, adaptive, and error-controlled sequential tests.
Robust tests control type I error under data corruption.
problem Effective hypothesis testing under data corruption.
method General permutation tests using kernel MMD and HSIC metrics.
result Robust tests are minimax optimal and outperform private tests.
New attacks improve privacy audits by analyzing model updates.
problem Improving privacy audits of AI models through sequence analysis.
method Developed SeMI attacks to identify target insertions in model sequences.
result SeMI attacks achieve higher power and tighter privacy audits.
Study improves CI tests for relational data to robustly discover causal structures.
problem Learning causal relationships from relational data.
method Conduct CI tests against relational data to robustly recover causal structure.
result Effective approach demonstrated through experiments.
Paper analyzes privacy risks of learning complex models.
problem Privacy leakage from learning high-dimensional graphical models.
method Theoretical analysis of tracing attacks on Bayesian networks.
result Provides a tight upper bound on tracing attack power.
Study on testing two populations with confounders.
problem Determining if two populations have the same distribution after accounting for confounding factors.
method Introduce two general frameworks for conditional two-sample testing.
result Demonstrated the power and validity of the proposed frameworks.
A new measure equitability helps identify significant relationships in high-dimensional data.
problem Identifying significant relationships in high-dimensional datasets with many weak relationships.
method Formalizes equitability as a property of measures of dependence, introduces interpretable intervals, and uses hypothesis testing equivalence.
result Equitability allows for well-powered tests distinguishing between trivial and non-trivial relationships and different strengths.
Enhances power of covariance matrix tests for high-dimensional data.
problem Testing large covariance matrices in high-dimensional data.
method Proposes a new Fisher's combined probability test for quadratic form and maximum form statistics.
result Boosts power against more general alternatives.
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.
Decentralized detection avoids sharing data, controls false discoveries.
problem Global false discovery rate control in decentralized novelty detection.
method Quantized surrogate models for low-precision sharing, preserving exchangeability.
result Quantized composite scores maintain competitive statistical power with reduced communication.
New statistics improve kernel independence testing efficiency.
problem Improving efficiency in kernel independence testing.
method Adapting martingale MMD construction to joint independence problem.
result Two new statistics achieve finite-sample consistency with linear per-test cost.
New methods for CI testing under model misspecification.
problem Challenges in CI testing with misspecified models.
method Proposes new approximations and upper bounds for testing errors of regression-based CI tests.
result Introduces the Rao-Blackwellized Predictor Test (RBPT) robust against misspecified inductive biases.
A new test validates ensemble models against the null hypothesis.
problem Validating ensemble models against the null hypothesis of a constant response.
method Randomized permutation test on SVEM model predictions.
result The test maintains Type I error rate even with more parameters than observations.
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.
Paper introduces MIC*, a new measure of dependence that is equitable and powerful.
problem Finding the strongest relationships in high-dimensional data sets.
method Introduces MIC*, a population measure of dependence, and defines three ways to view it. Proposes efficient algorithms for computing MIC* and a consistent estimator MICe.
result MICe and TICe show better equitability and power against independence.
AvaGrad optimizes vision tasks by decoupling learning rate and adaptability.
problem Improving optimization methods for vision tasks.
method Derives AvaGrad, a new optimizer that decouples learning rate and adaptability.
result AvaGrad outperforms SGD on vision tasks when adaptability is properly tuned.
Gaussian kernel tests are optimal against smooth alternatives.
problem Understanding the statistical properties of nonparametric tests using Gaussian kernels.
method Analysis of Gaussian kernel-based goodness-of-fit, homogeneity, and independence tests.
result Gaussian kernel tests are minimax optimal against smooth alternatives in all three settings.
This paper explores how temporal dependency in audio data can improve robustness against adversarial examples.
problem Mitigating adversarial examples in audio data.
method Exploiting temporal dependency to gain discriminative power against audio adversarial examples.
result Temporal dependency can be used to resist adaptive attacks on audio adversarial examples.
A new test improves feature evaluation in predictive models.
problem Evaluating the usefulness of features in supervised prediction problems.
method Proposes a novel conditional independence test using permutation testing.
result Achieves better predictive power than competing approaches.
Modeling financial returns as conditionally independent random variables explains power-law tails.
problem Understanding the distribution of financial returns and their relation to volatility.
method Assuming returns are conditionally independent given volatility, which varies randomly over time.
result Returns distribution can be described by the sum of conditionally independent random variables, showing scaling and power-law tails.
Discusses MultiFIT for multivariate dependence, comparing it to HSIC tests.
problem Comparing Multiscale Fisher's Independence Test (MultiFIT) to HSIC tests for multivariate dependence.
method Compares MultiFIT to HSIC tests, highlighting exact level control and performance limitations.
result Observes performance limitations of MultiFIT in terms of test power.
The grid integration of intermittent Renewable Energy Sources (RES) causes costs for grid operators due to forecast uncertainty and the resulting production schedule mismatches. These so-called profile service costs are marginal cost components and can be understood as an insurance fee against RES production schedule u…
We provide a unifying framework linking two classes of statistics used in two-sample and independence testing: on the one hand, the energy distances and distance covariances from the statistics literature; on the other, maximum mean discrepancies (MMD), that is, distances between embeddings of distributions to reproduc…
This work improves independence tests for high-dimensional data.
problem Detecting subtle dependencies between high-dimensional random variables with complex distributions.
method Develops two approaches to learn powerful independence tests using variational mutual information and HSIC.
result Optimized HSIC tests generally outperform other approaches on detecting structured dependence.
Unified CI test for categorical and ordinal data maintains power in high dimensions.
problem Rapid degradation of statistical power in existing CI tests for high-dimensional conditioning variables.
method Unified CI test for categorical and ordinal data, maintaining reasonable calibration and power in high dimensions.
result Our test outperforms existing baselines in model testing and structure learning for dense directed graphical models.
We prove that Hamiltonian characteristic classes defined as fibre integrals of powers of the coupling class are algebraically independent for generic coadjoint orbits.
New voting rules protect against strategic voting by robust statistics.
problem Strategic voting can skew election outcomes.
method Revisit Mallows model, develop robust estimator.
result Efficient estimator achieves nearly optimal robustness.
Superposition accelerates training to a universal power-law exponent.
problem Training dynamics in neural networks.
method Teacher-student framework and analytic theory.
result Superposition leads to a universal power-law exponent of ~1, independent of data and channel statistics.
RTFE provides adversarial robustness to multiple models.
problem Adversarial examples can transfer to other models, compromising robustness.
method Proposes RTFE, a deep learning-based pre-processing mechanism.
result RTFE provides adversarial robustness to multiple independently trained classifiers.
In sequential anytime-valid inference, any admissible procedure must be based on e-processes: generalizations of test martingales that quantify the accumulated evidence against a composite null hypothesis at any stopping time. This paper proposes a method for combining e-processes constructed in different filtrations b…
Adversaries with multiple antennas can fool deep learning modulators more effectively.
problem Improving evasion attacks on deep learning-based modulation classifiers.
method Utilizing multiple antennas to enhance adversarial attacks on deep learning classifiers.
result Adversarial attacks with multiple antennas significantly improve classifier accuracy.
FMCIT accelerates CI tests for causal discovery, maintaining power and efficiency.
problem High computational complexity in CI tests limits practical applicability of causal discovery methods.
method Flow Matching-based Conditional Independence Test (FMCIT) that leverages flow matching for fast CI tests.
result FMCIT effectively controls type-I error and maintains high testing power under the alternative hypothesis.
Enhances single-step adversarial training to defend against iterative adversarial examples.
problem Defending against iterative adversarial examples in neural networks.
method Identified and leveraged empirical properties of Iter-Adv to improve Single-Adv.
result Enhanced Single-Adv to defend against iterative adversarial examples with improved accuracy and reduced training cost.