New ICA method improves on existing techniques.
problem Finding independent components in data.
method Multiple-weighted Independent Component Analysis (MWeICA) based on approximate diagonalization of weighted covariance matrices.
result MWeICA achieves better results than state-of-the-art ICA methods with similar computational time.
This work develops a non-parametric test for relational independence in non-i.i.d. data.
problem Testing independence in relational systems where data samples are not i.i.d.
method Kernel mean embedding for relational variables, consistent non-parametric scalable kernel test.
result Empirically validated effectiveness compared to state-of-the-art tests.
Extracts the finest pattern of mutual independence from data.
problem Inferring the finest mutual independence pattern from data.
method Estimate the set of valid patterns of dichotomic independence and use their intersection to infer the finest pattern.
result The method can estimate the finest mutual independence pattern from i.i.d. realizations of a multivariate normal distribution.
New method identifies causal structure in exchangeable data.
problem Existing causal discovery methods struggle with i.i.d. data.
method Exchangeable data provides richer conditional independence structure.
result Exchangeable data allows for unique causal structure identification.
This research designs a data-driven partition to test independence between continuous variables.
problem Testing independence between continuous random variables.
method Empirical log-likelihood statistic and data-driven tree-structured partition.
result Strongly consistent test of independence over probability families.
New method recovers causal order from dependent data.
problem Causal discovery methods fail with shared volatility or common scale effects.
method Linear Mean-Independent Acyclic Model (LiMIAM) with mean-independence restrictions.
result Compatible causal order can be recovered from dependent disturbances.
Estimates marginal independence structure of Bayesian networks from data.
problem Learning the marginal independence structure of Bayesian networks from observational data.
method Using Gröbner basis and MCMC method (GrUES) to connect and recover the true structure.
result GrUES recovers the true marginal independence structure at a higher rate than simple independence tests.
The paper shows how to infer conditional independence from non-Gaussian data.
problem Inferring conditional independence from non-Gaussian distributions.
method Developed a method to recover conditional independence structure from the precision matrix of generalized nonparanormal data.
result The conditional independence structure can be inferred from the precision matrix of generalized nonparanormal data.
A new method tests independence for causal discovery on discrete data.
problem Inferring causal directions on discrete and categorical data.
method Subsampling-based method to test independence between cause and mechanism.
result Our method works for both discrete and categorical data without functional model assumptions.
New test detects independence in streaming data, adapting to data complexity.
problem Independence testing in streaming data with adaptive stopping.
method Sequential kernelized independence tests using betting principles.
result Valid inference in streaming data with improved power.
A new method tests conditional independence by transforming it into an unconditional problem using transport maps.
problem Testing conditional independence between two random vectors given a third.
method Constructing transport maps to transform conditional independence into unconditional independence, estimating these maps from data using conditional continuous normalizing flow models.
result The proposed method is validated through simulations and real-data analysis, demonstrating practical effectiveness.
New method allows generating independent data matrices from summary statistics.
problem Generating independent data matrices from summary statistics like mean and covariance.
method Thinning a Wishart random matrix based on sample mean and covariance.
result It is possible to generate two independent data matrices from summary statistics.
New algorithm reduces conditional independence tests needed for causal discovery.
problem Efficiently infer causal relations from observational data.
method Established an algorithm with complexity pO(s) tests. result Achieves exponent-optimality up to a logarithmic factor in terms of conditional independence tests.
A new graphical model for discrete data without parametric restrictions.
problem Discrete data modeling with restrictions.
method Additive conditional independence and penalized estimation of precision operator.
result Consistency of the estimator in ultrahigh-dimensional settings.
New methods infer causal structure from data without hidden variables.
problem Inferring causal structure from observational data with hidden variables.
method Introduces alternative independence tests and conditionally-additive-noise models.
result Can infer causal relations without assumptions about equation form or hidden variables.
New test SCI for conditional independence on discrete data improves accuracy in causal discovery.
problem Testing conditional independence on discrete data often fails in practice.
method Proposes a new test based on stochastic complexity for discrete data.
result SCI is an asymptotically unbiased and L2 consistent estimator for conditional mutual information (CMI).
New method uses MMD estimators to enforce model invariance with missing data.
problem Models trained on missing data can fail on related test distributions.
method Derives MMD estimators for enforcing model invariance under missing nuisances.
result Optimizing through MMD estimates achieves similar test performance to using full data.
Entropy regularized OT test assesses independence between samples.
problem Testing independence between two samples.
method Entropy regularized optimal transport.
result Non-asymptotic bounds for test statistic established.
Kernel-based tests detect dependencies in multivariate time series, including stationary and non-stationary data.
problem Detecting dependencies in multivariate time series data, especially non-stationary data.
method Kernel-based statistical tests of joint independence, extending dHSIC to handle both stationary and non-stationary processes.
result Robustly uncovers significant higher-order dependencies in synthetic and real-world data.
We study 'meta-dependence' in conditional independence tests across different empirical distributions.
problem Understanding the breakdown of conditional independence properties in finite data.
method Geometric intuition and information projections to measure meta-dependence between conditional independences.
result We provide a measure of meta-dependence that consolidates findings across synthetic and real-world data.
Dream Distillation compresses models without data, achieving high accuracy.
problem Model compression without real data.
method Data-independent model compression framework.
result Achieves 88.5% accuracy on CIFAR-10 test set.
Paper develops streaming algorithms to estimate classifier accuracy on unlabeled data.
problem Estimating classifier accuracy on unlabeled data with noisy decisions.
method Two algebraic evaluators: majority voting and a novel method to handle correlated classifiers.
result The novel method can be as accurate as 1% when handling small amounts of correlation.
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.
Bayesian method finds patterns of mutual independence in data.
problem Investigating mutual independence in statistics.
method Bayesian model comparison using Markov chain Monte Carlo (MCMC).
result Automated search for patterns of mutual independence.
Independent component analysis (ICA) is a powerful method for blind source separation based on the assumption that sources are statistically independent. Though ICA has proven useful and has been employed in many applications, complete statistical independence can be too restrictive an assumption in practice. Additiona…
ACID neural network tests conditional independence efficiently.
problem Testing conditional independence in data.
method Amortized conditional independence testing using transformer-based neural networks.
result ACID achieves state-of-the-art performance and robust generalization.
Learning the Markov network structure from data is a problem that has received considerable attention in machine learning, and in many other application fields. This work focuses on a particular approach for this purpose called independence-based learning. Such approach guarantees the learning of the correct structure …
The paper tackles extrapolation in generative models by enforcing independence of mechanisms.
problem How to make generative models extrapolate to new, unseen environments?
method Developed a theoretical framework for independence of mechanisms, demonstrated on toy examples and real-world data.
result Extrapolation capabilities of generative models can be improved by enforcing independence of mechanisms explicitly during training.
GTMs model complex multivariate data with varying conditional independencies.
problem Modeling multivariate data with intricate marginals and complex dependency structures.
method Semiparametric approach using penalized splines and lasso regularization.
result GTMs accurately learn complex dependencies and identify conditional independencies.
Novel tests for genetic independence in high-dimensional data.
problem Testing independence in genetics studies with many variables.
method Defining premetric structures on genetic data support spaces.
result Solid theoretical framework and computationally-efficient implementations.
Modeling data as being sampled from a union of independent subspaces has been widely applied to a number of real world applications. However, dimensionality reduction approaches that theoretically preserve this independence assumption have not been well studied. Our key contribution is to show that 2K projection vect…
A new test detects non-linear independence in censored survival data.
problem Detecting non-linear independence between survival times and covariates.
method A kernel log-rank test using reproducing kernel Hilbert spaces.
result The test correctly rejects the null hypothesis under any alternative.
Detect hidden confounding in observational data using multiple environments.
problem Detect hidden confounding in observational data.
method Theoretical framework and simulation studies to test for hidden confounding.
result The proposed procedure correctly predicts hidden confounding, especially when bias is large.
New method tests independence in time series data.
problem Testing independence between time series data.
method Temporal dependence statistic with block permutation.
result Asymptotically valid and universally consistent test for independence.
TCRI improves domain generalization by enforcing conditional independence constraints.
problem Limitations of existing domain generalization methods due to incomplete constraints.
method TCRI implements regularizers motivated by conditional independence constraints.
result TCRI achieves cross-domain stability and outperforms baselines in worst-domain accuracy.
A Closer Look at Disentangling in β-VAE shows non-monotonic inference performance.
problem Learning disentangled representations from data.
method Generalization of VAE using variational inference with hyperparameter β.
result Non-monotonic inference performance in β-VAE with a finite optimal β.
New approach to disentangled representations using mutual information.
problem Disentangled representations lack sufficient inductive biases.
method Formulate disentanglement through mutual information and conditional independence.
result Violation of mutual information assumption leads to loss of disentanglement.
Study shows priors are crucial for accurate causal learning from unlabeled data.
problem Improving causal learning from unlabeled data.
method Investigated causal learning using Bayesian methods and analyzed the impact of priors.
result Factorized priors lead to factorized posteriors, aligning with independent causal mechanisms.
Model-X test detects conditional independence in streaming data.
problem Detecting conditional independence in data streams with arbitrary dependency.
method Sequential testing inspired by model-X and testing by betting.
result Significantly reduces type-I error rate and enhances data efficiency.
We show that the error probability of reconstructing kernel matrices from Random Fourier Features for the Gaussian kernel function is at most O(R2/3exp(−D)), where D is the number of random features and R is the diameter of the data domain. We also provide an information-theoretic method-independen…
Method separates data into class and style factors using semi-supervised learning.
problem Separating generative factors of data into class and style vectors.
method Independent Vector Variational Autoencoders with semi-supervised learning and independence term.
result Improves classification performance and generation controllability.
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.
MixCIT tests conditional independence for mixed data types efficiently and reliably.
problem Testing conditional independence for mixed data types, especially when at least one is continuous.
method Graph-based test statistic comparing kernel similarities, debiased local-polynomial approach for continuous variables.
result Unified, efficient, and statistically guaranteed solution across heterogeneous data types.
Independent Component Analysis (ICA) is a technique for unsupervised exploration of multi-channel data that is widely used in observational sciences. In its classic form, ICA relies on modeling the data as linear mixtures of non-Gaussian independent sources. The maximization of the corresponding likelihood is a challen…
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.
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.
New findings show independent subordination is not relevant for accurate option pricing.
problem Determining if independent subordination improves option pricing accuracy.
method Utilized a class of additive processes (ATS) to demonstrate that independent subordination is incompatible with market data and shows worse calibration performances.
result Independent subordination is not relevant for accurate option pricing, as shown by the ATS class of processes.
New algorithms learn simple staged trees from data, improving model fit.
problem Complex conditional independences in categorical data vectors.
method Structural learning algorithms for simple staged trees, coalescing the underlying tree.
result Data-learned simple staged trees often outperform Bayesian networks in model fit.