EFDM models spatial point processes with variable cardinality using existence variables.
problem Challenges in extending diffusion models to variable-cardinality spatial point processes.
method Existence-field diffusion model (EFDM) that jointly models spatial locations and cardinality without discrete transitions.
result EFDM achieves improved modeling capability on datasets with varying cardinality.
Proposes a two-stage method for selecting correlated predictors in high-dimensional data.
problem Selecting correlated predictors in high-dimensional data with unknown group structures.
method Two-stage approach: variable clustering followed by group selection.
result The two-stage method improves prediction accuracy and active predictor selection.
New method integrates latent variables for Bayesian Optimization of materials with both qualitative and quantitative factors.
problem Bayesian Optimization for materials design with mixed qualitative and quantitative variables.
method Integrates latent variables for mixed-variable Gaussian process modeling within the Bayesian Optimization framework.
result LVGP provides superior modeling accuracy compared to existing methods for mixed-variable problems.
We study the problem of learning latent variables in Gaussian graphical models. Existing methods for this problem assume that the precision matrix of the observed variables is the superposition of a sparse and a low-rank component. In this paper, we focus on the estimation of the low-rank component, which encodes the e…
The paper identifies causal effects in latent variable models using higher-order cumulants.
problem Challenges in identifying causal effects in latent variable models with latent confounders.
method Using higher-order cumulants, the paper addresses two challenging setups: a single proxy variable and underspecified instrumental variables.
result Causal effects are identifiable with a single proxy or instrument.
Study improves model estimation and variable selection using GANs with Lasso penalty.
problem Variable selection in high-dimensional data with deep networks.
method Conditional Wasserstein Generative Adversarial Networks with Group Lasso penalization.
result Established convergence rate for variable selection in censored survival data.
Sharp concentration results for sums of heavy-tailed random variables.
problem Analyzing sums of independent heavy-tailed random variables.
method Using concentration inequalities and large deviation principles for distributions satisfying specific tail bounds.
result Sharp concentration inequalities and large deviation results for sums of heavy-tailed random variables.
We apply a wild bootstrap method to the Lancaster three-variable interaction measure in order to detect factorisation of the joint distribution on three variables forming a stationary random process, for which the existing permutation bootstrap method fails. As in the i.i.d. case, the Lancaster test is found to outperf…
New method identifies causal relationships in presence of hidden variables.
problem Identifying causal relationships when hidden variables exist.
method Established sufficient conditions and introduced a search algorithm.
result Proved soundness and completeness of the search algorithm.
Study optimal adjustment sets for causal policies with hidden variables.
problem Estimating dynamic treatment regimes with hidden variables.
method Developed criteria for graphs without hidden variables to compare estimators, extended to dynamic policies and hidden variables.
result Existence and computation of optimal minimal and globally optimal adjustment sets.
A tensor field generates separation of variables for certain metrics.
problem Finding metrics with specific tensor field properties.
method Constructing differential invariants for a (1,1)-tensor field. result Explicit system of invariants for metrics generating separation of variables.
We use the score function for causal discovery, tackling challenges with hidden variables.
problem Causal discovery from observational data with hidden variables.
method Fine-tuning identifiability results, establishing conditions for inferring causal relations from the score, proposing a flexible algorithm.
result Empirical validation of the proposed algorithm for causal discovery on linear, nonlinear, and latent variable models.
Optimal sampling strategy improves prediction accuracy with surrogate variables under measurement constraints.
problem Measurement-constrained datasets and lack of labeled data.
method A-optimality criterion for optimal sampling, leveraging surrogate variables.
result Achieves lower asymptotic variance and reduced empirical mean squared error.
In this paper we analyze the obstructions to the existence of global action-angle variables for regular non-commutative integrable systems (NCI systems) on Poisson manifolds. In contrast with local action-angle variables, which exist as soon as the fibers of the momentum map of such an integrable system are compact, gl…
TPLVM models portfolio construction for non-Gaussian financial data.
problem Optimal asset allocation in finance with non-Gaussian fluctuations.
method Student's t-process latent variable model (TPLVM) for portfolio optimization.
result TPLVM outperforms Gaussian process latent variable model in minimum-variance portfolio construction.
Study on nonlinear elliptic equations with variable exponents, proving existence and multiplicity of solutions.
problem Existence and multiplicity of solutions for Dirichlet boundary value problems involving (p(m),q(m))-equation. method Proved using the mountain pass theorem and Fountain theorem with Cerami sequences.
result Existence and multiplicity of solutions for (p(m),q(m))-equation. In this paper we develop a general conceptual approach to the problem of existence of action-angle variables for dynamical systems, which establishes and uses the fundamental conservation property of associated torus actions: anything which is preserved by the system is also preserved by the associated torus actions. T…
A new method for efficient inference in probabilistic programs with mixed support.
problem Challenges in inference for programs with both continuous and discrete latent variables.
method Stochastic gradient Markov Chain Monte Carlo algorithms.
result Outperforms existing composing inference baselines and works almost as well as inference in marginalized versions.
New score-based methods identify causal structures with latent variables.
problem Identifying causal structures involving latent variables.
method Score-based methods with identifiability guarantees.
result Score equivalence and consistency for latent variable causal models.
Two ANOVA-based algorithms boost random Fourier feature models for function approximation.
problem Approximating high-dimensional functions with low-order interactions.
method Utilizes ANOVA decomposition to learn low-order functions and index sets of important variables.
result Significantly reduces approximation error compared to existing methods.
Paper tackles causal effect estimation in observational data with hidden variables.
problem Estimating causal effects in observational data with hidden confounders.
method Developed a theorem for local search to find superset of adjustment variables, proposing a data-driven algorithm.
result Proposed algorithm produces more accurate causal effect estimates than existing methods.
Unified Bayesian Optimisation for mixed variables improves performance.
problem Efficient optimisation of problems with both categorical and continuous variables.
method Derive value proposals from the Expected Improvement criterion to optimise both categorical and continuous variables under a single acquisition metric.
result Unified approach significantly outperforms existing methods across mixed-variable tasks.
We classify the dispersive Poisson brackets with one dependent variable and two independent variables, with leading order of hydrodynamic type, up to Miura transformations. We show that, in contrast to the case of a single independent variable for which a well known triviality result exists, the Miura equivalence class…
CLOUD method detects causal relationships in various data types without latent variable assumptions.
problem Detecting causal relationships in the presence of unobserved common causes.
method CLOUD method using Normalized Maximum Likelihood (NML) Code for various data types (discrete, mixed, continuous).
result CLOUD method is more effective than existing methods in inferring causal relationships.
Variable selection for models including interactions between explanatory variables often needs to obey certain hierarchical constraints. The weak or strong structural hierarchy requires that the existence of an interaction term implies at least one or both associated main effects to be present in the model. Lately, thi…
An econometric or statistical model may undergo a marginal gain if we admit a new variable to the model, and a marginal loss if we remove an existing variable from the model. Assuming equality of opportunity among all candidate variables, we derive a valuation framework by the expected marginal gain and marginal loss i…
Proposes a method to combine datasets with missing values using Gaussian process latent variables.
problem Combining datasets with missing values under non-Missing at Random (NMAR) missingness.
method Gaussian process latent variable model for non-MAR missing data.
result Valid estimates are obtained using the proposed method, while existing methods provide severely biased estimates.
A framework for measuring differences in categorical data.
problem Measuring differences between categorical variables.
method Introduces a general framework for efficient and flexible implementation of distances for categorical variables.
result Framework allows for incorporation of existing distances and introduces new formulations.
New algorithm groups variables by ancestral relationships to improve causal graph estimation accuracy.
problem Difficulty in estimating causal graphs with small sample sizes relative to variables.
method CAG algorithm groups variables based on ancestral relationships, reducing complexity and improving accuracy.
result CAG outperforms existing methods in estimation accuracy and computation time.
We show that the Alexander-Conway polynomial Delta is obtainable via a particular one-variable reduction of each two-variable Links-Gould invariant LG^{m,1}, where m is a positive integer. Thus there exist infinitely many two-variable generalisations of Delta. This result is not obvious since in the reduction, the repr…
New model tackles causal bandits with dependent variables.
problem Understanding reward-maximizing interventions in causal networks with dependent variables.
method Introduces hierarchical causal bandit model with a contextual variable capturing interactions among variables.
result Derives nearly matching regret bounds for binary context in causal bandits with dependent arms.
We characterize and study variable importance (VIMP) and pairwise variable associations in binary regression trees. A key component involves the node mean squared error for a quantity we refer to as a maximal subtree. The theory naturally extends from single trees to ensembles of trees and applies to methods like rando…
Bayesian Optimization framework tackles materials design challenges with mixed variables.
problem Challenges in materials design due to mixed qualitative and quantitative variables, limited data, and high simulation costs.
method Data-centric, mixed-variable Bayesian Optimization framework using Latent Variable Gaussian Process (LVGP) and Expected Improvement acquisition function.
result Locates optimal design for insulating polymer nanocomposites efficiently.
There has been much recent, exciting work on combining the complementary strengths of latent variable models and deep learning. Latent variable modeling makes it easy to explicitly specify model constraints through conditional independence properties, while deep learning makes it possible to parameterize these conditio…
Knoop enhances variable selection with over-parameterization and knockoffs.
problem Challenges of variable selection in high-dimensional datasets.
method Generates knockoff variables, integrates them into an over-parameterized model, and uses anomaly-based significance tests.
result Superior performance in variable selection compared to existing methods.
A simple thresholding technique improves graph selection in neural connectivity studies.
problem Graphical model selection for functional neural connectivity in the presence of latent variables.
method Apply a hard thresholding operator to graphical Lasso, neighborhood selection, or CLIME estimators.
result Thresholded estimators outperform existing methods in graph selection consistency and empirical results.
Observed associations in a database may be due in whole or part to variations in unrecorded (latent) variables. Identifying such variables and their causal relationships with one another is a principal goal in many scientific and practical domains. Previous work shows that, given a partition of observed variables such …
New method disentangles latent variables in nonstationary data.
problem Disentangling latent variables in nonstationary sequential data.
method NCTRL framework exploiting Markov assumption and temporal structure.
result Independent latent components can be recovered from nonlinear mixture without auxiliary variables.
Variational autoencoders often collapse, showing latent variables are non-identifiable.
problem Posterior collapse in variational autoencoders due to non-identifiable latent variables.
method Proves latent variable non-identifiability causes posterior collapse. Proposes latent-identifiable models using Brenier maps and input convex neural networks.
result Latent-identifiable models resolve posterior collapse and provide meaningful representations.
We consider the Granger causal structure learning problem from time series data. Granger causal algorithms predict a 'Granger causal effect' between two variables by testing if prediction error of one decreases significantly in the absence of the other variable among the predictor covariates. Almost all existing Grange…
Paper generalizes bipolar theorems for non-negative random variables.
problem Problems with existing bipolar theorems under stronger assumptions.
method Generalizes existing theorems in a robust probabilistic framework.
result Provides necessary and sufficient conditions for bipolar representation.
SurvNet selects important variables in DNNs with false discovery rate control.
problem Variable selection in deep neural networks (DNNs) for interpretability.
method Backward elimination procedure based on a new variable importance measure.
result SurvNet estimates and controls false discovery rate of selected variables.
Paper proposes a new method to identify causal graphs with latent variables using higher-order cumulants.
problem Estimating causal directed acyclic graphs with latent confounders.
method Uses higher-order cumulants to identify causal structures among observed and latent variables.
result Validates the proposed algorithm through simulations and real-world data.
In this work we study convex relaxations of quadratic optimisation problems over permutation matrices. While existing semidefinite programming approaches can achieve remarkably tight relaxations, they have the strong disadvantage that they lift the original n×n-dimensional variable to an n2×n2-d…
Paper proposes methods to discover causal models with unobserved variables.
problem Discovering causal relationships in data with unobserved variables.
method Two methods leveraging prior knowledge for causal discovery in CAM-UV models.
result Accuracy of causal discovery improves with more prior knowledge.
Paper extends stochastic dominance for compound binomial distributions.
problem Stochastic dominance for infinite-mean random variables.
method Investigates properties and inclusion relationships of distribution classes, extends results to compound binomial distributions.
result Establishes necessary and sufficient conditions for first-order stochastic dominance preservation.
New method reconstructs missing variables in time series using autoencoders and automatic differentiation.
problem Reconstruct missing variables in time series with flexible input and output combinations.
method Train an autoencoder with all features, optimize missing variables as inputs, and use automatic differentiation.
result Flexible input and output combinations can be achieved without retraining the autoencoder.
A new test for conditional independence in discretized data.
problem Testing conditional independence when only discretized observations are available.
method Proposes a conditional independence test designed for discretized observations, using bridge equations to recover latent variables' information.
result Demonstrates the effectiveness of the proposed test through theoretical and empirical validation.