On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “kernel-based SEMs”

Kernel-Based Structural Equation Models for Topology Identification of Directed Networksstat.ML

Novel kernel-based SEMs improve edge detection in directed networks.

problem Detecting causal interactions in complex directed networks.

method Advocates nonlinear SEMs using kernels for nonlinear dependencies, proposing a convex regularized estimator with efficient optimization methods.

result Novel kernel-based approach outperforms linear SEMs in edge detection, revealing new regulatory edges.

kernel-based SEMs nonlinear dependencies directed networks edge detection gene expression

2016-05-10abs ↗pdf ↗

Learning Bidirectional Causal Interactions with Heteroscedastic Neural Networksstat.ML

SEM-DNN learns reciprocal interactions from observational data without external instruments.

problem Estimating bidirectional interactions from endogenous data.

method Heteroscedastic neural simultaneous-equation estimator (SEM-DNN) that learns reciprocal structural interactions.

result SEM-DNN recovers structural effects more reliably than other methods under increasing information.

causal inference neural networks heteroscedasticity simultaneous equations endogeneity

2026-07-24abs ↗pdf ↗

Sinkhorn EM: An Expectation-Maximization algorithm based on entropic optimal transportstat.ML

sEM uses optimal transport to improve EM algorithm for better convergence and avoiding local optima.

problem Improving the EM algorithm for better convergence and avoiding local optima.

method sEM uses entropic optimal transport to compute responsibilities in the expectation step, leading to better global convergence guarantees and avoiding local optima.

result sEM learns cell labels significantly better than other approaches, improving convergence and avoiding local optima.

EM algorithm optimal transport sinkhorn divergence convergence local optima

2020-06-30abs ↗pdf ↗

From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Researchcs.LG

Study combines SEM, OLS, and DML for robustness checks in survey-based research.

problem Stability of SEM findings under alternative estimation frameworks.

method Staged robustness analysis framework connecting SEM, OLS, and DML.

result Identifies stable and unstable relationships across SEM, OLS, and DML checks.

Structural Equation Modeling Double Machine Learning Survey Research Robustness Analysis Latent Constructs

2026-07-01abs ↗pdf ↗

Analyzing the Interpretability Robustness of Self-Explaining Modelscs.LG

SEMs fail to provide robust explanations to adversarial inputs.

problem Lack of robustness in interpretability of self-explaining models.

method Evaluation of current SEMs and creation of adversarial inputs.

result Adversarial inputs can cause significant changes in explanations without affecting model outputs.

self-explaining models interpretability robustness adversarial inputs model robustness

2019-05-27abs ↗pdf ↗

Causal Consistency of Structural Equation Modelsstat.ML

Consistent SEMs predict the same effects of interventions.

problem Consistency of causal models in SEMs.

method Formalised consistency of SEMs through transformations, emphasizing well-specified interventions.

result Causal models at different levels of detail are consistent.

structural equation models causal consistency interventions transformations system modelling

2017-07-04abs ↗pdf ↗

Direct Learning with Guarantees of the Difference DAG Between Structural Equation Modelsstat.ME

Paper directly estimates structural difference between SEMs from samples.

problem Estimating change in causal relationships between two conditions.

method Principled algorithm that recovers structural difference SEM in O(d^2 log p) samples.

result Method outperforms state-of-the-art and validates usefulness in medical domain.

structural equation models causal inference difference estimation sample complexity medical domain

2019-06-28abs ↗pdf ↗

Covariance-Based Structural Equation Modeling in Small-Sample Settings with

p>n

cs.LG

Novel approach for SEM in small samples with $p>n$ .

problem Small sample size and

p>n

issues in factor-based SEM.

method Reformulates covariance structure into self-covariance and cross-covariance, defines a feasible set with relative error constraint.

result Improved stability and directional information in small-sample settings.

covariance-based SEM small sample p>n likelihood-based estimation feasible set

2026-04-18abs ↗pdf ↗

Nonlinear Structural Vector Autoregressive Models for Inferring Effective Brain Network Connectivitystat.AP

New model infers brain connectivity using nonlinear SVARMs.

problem Inferring effective brain network connectivity.

method Kernel-based nonlinear structural vector autoregressive models (SVARMs).

result Unveils previously unknown causal links between brain regions.

brain connectivity vector autoregressive models nonlinear dependencies kernel methods sparsity

2016-10-20abs ↗pdf ↗

Learning linear structural equation models in polynomial time and sample complexitycs.LG

New algorithm learns linear SEMs efficiently from data.

problem Learning linear structural equation models from observational data.

method Developed an efficient algorithm for linear SEMs with arbitrary noise.

result Algorithm recovers DAG structure under general identifiability conditions.

structural equation models linear SEMs causal inference computational efficiency statistical efficiency

2017-07-15abs ↗pdf ↗

PAC Generalization via Invariant Representationscs.LG

The paper tackles generalization in machine learning by finding invariant representations of data.

problem Obtaining robust models that generalize well across different training environments.

method The paper introduces the concept of

ε

-approximate invariance to study the robustness of models to unseen SEMs.

result The paper provides finite-sample out-of-distribution generalization guarantees for approximate invariance in linear SEMs.

invariant representations generalization machine learning structural equation models PAC learning

2022-05-30abs ↗pdf ↗

Sub-Riemannian Snakes on the Projective Line Bundle with Applications to Segmentation of SEM Imagesmath.DG

A new snake model improves segmentation of SEM images.

problem Efficiently segmenting overlapping electronic structures in SEM images.

method Geodesic tracking on projective line bundle with a geometric criterion for switching between fast spatial snakes and minimizing geodesics.

result Improved robust and automatic segmentation of overlapping electronic structures in SEM images.

SEM images segmentation geodesic tracking projective line bundle snake model

2026-04-13abs ↗pdf ↗

Identifiability of Gaussian Structural Equation Models with Homogeneous and Heterogeneous Error Variancesstat.ML

New method identifies Gaussian SEMs with varying error variances.

problem Identify Gaussian SEMs with both homogeneous and heterogeneous error variances.

method Exploits error variances and edge weights; provides a statistically consistent and feasible structure learning algorithm.

result Proves identifiability of Gaussian SEMs with both homogeneous and heterogeneous unknown error variances.

structural equation models identifiability Gaussian SEMs error variances edge weights

2019-01-29abs ↗pdf ↗

SLEM: Machine Learning for Path Modeling and Causal Inference with Super Learner Equation Modelingstat.ML

SLEM uses machine learning to improve causal inference from observational data.

problem Improving causal inference from observational data using non-linear relationships.

method Super Learner Equation Modeling integrating machine learning ensembles.

result SLEM provides consistent and unbiased estimates of causal effects.

causal inference machine learning path modeling structural equation modeling Super Learner

2023-08-08abs ↗pdf ↗

Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approachstat.ML

New neural approach for estimating SEMs with provable convergence.

problem Estimating structural parameters in SEMs.

method Formulated as a min-max game with neural networks, learned using stochastic gradient descent.

result Global convergence in overparametrized regime, improving state-of-the-art.

structural equation models neural networks min-max game global convergence overparametrization

2020-07-02abs ↗pdf ↗

Consistent Bayesian causal discovery for structural equation models with equal error variancesmath.ST

Bayesian method recovers causal structure in SEMs with equal error variances.

problem Recovering causal structure in SEMs with equal error variances.

method Bayesian DAG selection method using g-priors and the key property of minimum expected squared errors.

result The method consistently recovers the true graph without additional distributional assumptions.

Bayesian causal discovery structural equation models equal error variances consistent recovery g-priors

2025-09-18abs ↗pdf ↗

A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answeringcs.CL

A new framework evaluates LLM calibration in open-ended QA.

problem Evaluating LLM calibration in open-ended QA settings.

method Sem-ECE framework: sampling answers, grouping by semantic classes, and using frequencies as confidence.

result Sem-ECE estimators are unbiased and Sem

_2

achieves smaller calibration error.

LLM calibration open-ended QA semantic sampling expected calibration error logit-based metrics

2026-05-08abs ↗pdf ↗

Causal network learning with non-invertible functional relationshipsstat.ML

Paper develops a method to learn causal networks with non-invertible functions.

problem Identifying causal relationships from observational data with non-invertible functional relationships.

method Proposes a test for non-invertible bivariate causal models and develops a method to incorporate this test in structure learning of DAGs.

result Our algorithms outperform existing DAG learning methods in identifying causal graphical structures.

causal network learning non-invertible functions nonlinear SEMs structure learning DAGs

2020-04-20abs ↗pdf ↗

Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithmscs.LG

New methods discover causal relationships from multiple related data views.

problem Causal discovery from non-Gaussian data.

method Multi-view linear Structural Equation Model (SEM) with weak assumptions.

result Identifiability of acyclic SEMs and successful causal graph estimation.

causal discovery multi-view data linear SEM non-Gaussianity structural equation model

2025-02-27abs ↗pdf ↗

Tensor Decompositions for Identifying Directed Graph Topologies and Tracking Dynamic Networksstat.ML

Novel tensor decomposition identifies directed network topologies from nodal data.

problem Identifying hidden directed network topologies from nodal data.

method Three-way tensor factorization using PARAFAC decomposition with second-order exogenous inputs.

result Topology can be identified from second-order exogenous inputs and time-varying factors.

tensor decomposition network topology PARAFAC SEM dynamic networks

2016-10-26abs ↗pdf ↗

Boosting Causal Additive Modelsstat.ML

Boosting method for causal SEMs from observational data.

problem Learning causal order among variables from observational data.

method Boosting-based approach with early stopping and component-wise gradient descent.

result Boosting with early stopping consistently favors the true causal ordering.

causal inference structural equation models observational data boosting gradient descent

2024-01-12abs ↗pdf ↗

Staged Mixture Modelling and Boostingcs.LG

In this paper, we introduce and evaluate a data-driven staged mixture modeling technique for building density, regression, and classification models. Our basic approach is to sequentially add components to a finite mixture model using the structural expectation maximization (SEM) algorithm. We show that our technique i…

2012-12-12abs ↗pdf ↗

Masked Gradient-Based Causal Structure Learningcs.LG

Paper learns causal structures from data using gradient-based optimization.

problem Learning causal structures from observational data.

method Reformulates SEM with binary adjacency matrix and uses gradient-based optimization.

result Gradient-based method efficiently identifies causal structures from data.

causal inference gradient optimization structural equation model binary adjacency matrix

2019-10-18abs ↗pdf ↗

A Theoretical and Experimental Comparison of the EM and SEM Algorithmcs.LG

In this paper we provide a new analysis of the SEM algorithm. Unlike previous work, we focus on the analysis of a single run of the algorithm. First, we discuss the algorithm for general mixture distributions. Second, we consider Gaussian mixture models and show that with high probability the update equations of the EM…

2013-10-18abs ↗pdf ↗

Loss convergence in a causal Bayesian neural network of retail firm performancestat.ML

Improved neural network convergence with causal Bayesian modeling in retail performance.

problem Improving neural network convergence in retail performance models.

method Causal Bayesian neural network implementation, removal of weakest SEM path, Flipout layers, Vadam optimizer.

result Neural network convergence improved with removal of the weakest SEM path.

neural networks causal modeling retail performance convergence Flipout layers

2020-08-29abs ↗pdf ↗

Parameter-wise co-clustering for high-dimensional datastat.ML

A new co-clustering model for high-dimensional data reduces parameter complexity.

problem High-dimensional data challenges traditional co-clustering methods.

method Parameter-wise co-clustering model with SEM and Gibbs sampler for estimation.

result The model maintains parsimony while offering more flexibility.

co-clustering high-dimensional data parameter-wise SEM Gibbs sampler

2018-08-25abs ↗pdf ↗

Learning Mixtures of Unknown Causal Interventionsstat.ML

New method disentangles mixed interventional and observational data in SEMs.

problem Learning causal relationships from mixed interventional and observational data.

method Developed a method to disentangle mixed interventional and observational data in linear SEMs with Gaussian noise.

result The method can identify causal graphs up to their interventional Markov Equivalence Class.

Causal Discovery Interventional Data Linear SEMs Gaussian Noise Markov Equivalence

2024-10-31abs ↗pdf ↗

Robust Causal Bandits for Linear Modelsstat.ML

This paper addresses robust CBs for linear SEMs with model fluctuations.

problem Designing interventions in causal systems with linear SEMs that are robust to model fluctuations.

method Develops a robust CB algorithm and analyzes its regret under model deviation.

result The proposed algorithm achieves nearly optimal

ilde{\mathcal{O}}(\sqrt{T})

regret when

C

o(\sqrt{T})

and maintains sub-linear regret for a broader range of

C

causal bandits linear SEMs model fluctuations cumulative regret sub-linear regret

2023-10-30abs ↗pdf ↗

A New Statistical Framework for Genetic Pleiotropic Analysis of High Dimensional Phenotype Datastat.ML

Develops a new statistical framework for analyzing genetic pleiotropy in high-dimensional phenotypes.

problem Limited analysis of genetic pleiotropy for high-dimensional phenotypes and genotypes.

method Sparse structural equation models (SEMs) extended to sparse functional SEMs, incorporating both common and rare variants, and using functional data analysis and ADMM techniques.

result Higher power to detect true causal genetic pleiotropic structures compared to existing methods.

genetic pleiotropy high dimensional phenotypes next-generation sequencing sparse structural equation models functional data analysis

2015-12-03abs ↗pdf ↗

Learning Sparse Nonparametric DAGsstat.ML

Framework for learning sparse DAGs from data.

problem Learning sparse directed acyclic graphs (DAGs) from data.

method Algebraic characterization of DAGs extended to nonparametric SEM, continuous optimization problem.

result General framework applicable to various nonparametric and semiparametric models.

DAGs nonparametric sparse structural equation models continuous optimization

2019-09-29abs ↗pdf ↗

Iterative Identification Closure: Amplifying Causal Identifiability in Linear SEMsstat.ML

IIC decouples causal identification into two phases, significantly reducing the HTC gap in linear SEMs.

problem Determining causal effect coefficients in linear SEMs with latent confounders using the Half-Trek Criterion (HTC) leaves a gap of inconclusive causal effects.

method Iterative Identification Closure (IIC) framework that decouples causal identification into two phases: a seed function S_0 and Reduced HTC propagation.

result IIC strictly subsumes both HTC and ancestor decomposition, reducing the HTC gap by over 80% with combined seeds.

causal inference linear structural equation models latent confounders Half-Trek Criterion seed function

2026-04-10abs ↗pdf ↗

Causal Bandits for Linear Structural Equation Modelsstat.ML

The paper tackles causal bandits for SEMs, proposing algorithms that avoid estimating $2^N$ reward distributions.

problem Designing an optimal sequence of interventions in causal graphical models to minimize cumulative regret.

method Proposes two algorithms for causal bandits for linear structural equation models (SEMs), avoiding the estimation of

2^N

reward distributions.

result Cumulative regrets scale as

ilde{\cal O} (d^{L+\frac{1}{2}} \sqrt{NT})

under bounded noise and parameter space.

causal bandits linear structural equation models interventions cumulative regret regression

2022-08-26abs ↗pdf ↗

Kernel-based Information Criterionstat.ML

This paper introduces Kernel-based Information Criterion (KIC) for model selection in regression analysis. The novel kernel-based complexity measure in KIC efficiently computes the interdependency between parameters of the model using a variable-wise variance and yields selection of better, more robust regressors. Expe…

2014-08-25abs ↗pdf ↗

On the robustness of kernel-based pairwise learningstat.ML

Paper shows robustness of kernel-based pairwise learning without strict assumptions.

problem Statistical robustness of kernel-based pairwise learning under minimal conditions.

method No assumptions on input and output spaces; derives influence function and robustness.

result Qualitative robustness of kernel-based estimator established.

robustness kernel-based pairwise learning influence function statistical

2020-10-29abs ↗pdf ↗

Generalized Kernel-Based Dynamic Mode Decompositioncs.LG

New algorithm improves dynamic mode decomposition for high-dimensional data.

problem Reduced modeling in high-dimensional spaces.

method Low rank constraint optimization and kernel-based computation.

result Gain in approximation accuracy and computational efficiency.

dynamic mode decomposition reproducing kernel Hilbert spaces non-linear dynamics kernel-based computation reduced modeling

2020-02-11abs ↗pdf ↗

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithmcs.LG

Kernel-based function approximation improves reinforcement learning performance.

problem Average reward reinforcement learning in infinite horizon settings.

method Optimistic algorithm based on kernel ridge regression.

result No-regret performance guarantees and confidence intervals for kernel-based predictions.

reinforcement learning kernel ridge regression average reward no-regret optimistic algorithm

2024-10-30abs ↗pdf ↗

BCD Nets: Scalable Variational Approaches for Bayesian Causal Discoverycs.LG

BCD Nets use variational inference to estimate DAGs with uncertainty.

problem Uncertainty in inferring causal graphs from limited data.

method Variational inference framework for Bayesian DAG estimation.

result BCD Nets outperform maximum-likelihood methods in low data regimes.

Bayesian causal discovery variational inference structural equation models discrete optimization low data regimes

2021-12-06abs ↗pdf ↗

Scalable Intervention Target Estimation in Linear Modelsstat.ME

Paper proposes scalable algorithm to estimate intervention targets in linear models.

problem Estimating intervention targets in linear models from observational and interventional data.

method The paper proposes a scalable algorithm that estimates intervention sites from the difference between precision matrices of observational and interventional datasets.

result The algorithm consistently identifies all intervention targets and updates observational Markov equivalence classes to interventional ones.

causal inference linear models interventional data precision matrices Markov equivalence

2021-11-15abs ↗pdf ↗

Kernel-based collocation methods for Heath-Jarrow-Morton models with Musiela parametrizationq-fin.CP

Kernel-based methods solve Heath-Jarrow-Morton models with Musiela parametrization.

problem Solving Heath-Jarrow-Morton models with Musiela parametrization.

method Kernel-based collocation methods as Euler-Maruyama approximations of stochastic differential equations.

result Derivation of a rate of convergence bound under specified conditions.

Heath-Jarrow-Morton models Musiela parametrization kernel-based methods stochastic differential equations Monte Carlo methods

2018-09-15abs ↗pdf ↗

Identifying Patient-Specific Root Causes of Diseasestat.ML

Identifies patient-specific root causes of disease using structural equation models.

problem Detecting significant variables in complex diseases that differ between patients.

method Defining patient-specific root causes as exogenous errors in a structural equation model, quantifying predictivity using Shapley values, and developing a fast algorithm called Root Causal Inference.

result Significant improvements in accuracy by uncovering root causes with large effect sizes at the individual level but clinically insignificant effect sizes at the group level.

structural equation modeling patient-specific root causes Shapley values root cause analysis disease prediction

2022-05-23abs ↗pdf ↗

Fast Bounded Online Gradient Descent Algorithms for Scalable Kernel-Based Online Learningcs.LG

Kernel-based online learning has often shown state-of-the-art performance for many online learning tasks. It, however, suffers from a major shortcoming, that is, the unbounded number of support vectors, making it non-scalable and unsuitable for applications with large-scale datasets. In this work, we study the problem …

2012-06-18abs ↗pdf ↗

Applied Causal Inference Powered by ML and AIecon.EM

Book introduces ML and AI for causal inference.

problem Uncertainty in causal relationships.

method Structural equation models, DAGs, SCMs, and Double/Debiased Machine Learning.

result Improved inference in causal models using predictive tools.

causal inference machine learning AI structural equation models structural causal models

2024-03-04abs ↗pdf ↗

Recovery Guarantees for Kernel-based Clustering under Non-parametric Mixture Modelscs.LG

Study provides guarantees for kernel clustering under non-parametric mixtures.

problem Statistical guarantees for kernel-based clustering without strong assumptions.

method Non-parametric mixture models, kernel-based clustering, consistency guarantees.

result Necessary and sufficient separability conditions for consistent clustering recovery.

kernel clustering non-parametric mixtures consistency guarantees separability conditions

2021-10-18abs ↗pdf ↗

Geometric Rates of Convergence for Kernel-based Sampling Algorithmsstat.ML

Kernel-based algorithms improve integral estimation with near-geometric speed.

problem Estimating integrals with target measures that are nearly atomic.

method Weighted kernel herding and sequential Bayesian quadrature.

result Near-geometric rate of convergence for nearly atomic target measures.

kernel-based sampling integral estimation geometric rate atomic measures quadrature

2019-07-19abs ↗pdf ↗

Kernel-based L_2-Boosting with Structure Constraintscs.LG

Kernel-based L2-boosting with structure constraints improves regression efficiency.

problem Developing efficient kernel methods for regression.

method Kernel-based re-scaled boosting with truncation (KReBooT).

result KReBooT achieves near overfitting resistance and sparse estimates.

kernel methods regression boosting structure constraints sparse estimate

2020-09-16abs ↗pdf ↗

Improved Bound for Robust Causal Bandits with Linear Modelsstat.ML

New algorithm reduces regret in CBs with time-varying models.

problem Designing robust interventions in CBs with unknown, fluctuating causal models.

method Proposes a robust CB algorithm with upper and lower bounds on regret.

result Achieves nearly optimal

ilde{\mathcal{O}}(\sqrt{T})

regret under certain conditions.

Causal Bandits Temporal Model Fluctuations Linear Structural Equation Models Cumulative Regret Optimal Regret

2024-05-13abs ↗pdf ↗

Learning Linear Polytree Structural Equation Modelsstat.ML

Researchers study learning polytree graphs from linear SEMs with exact recovery conditions.

problem Learning polytree graphs from linear SEMs with exact recovery conditions.

method Study Gaussian polytree models, derive sufficient and necessary conditions for sample sizes, and establish estimation error bounds.

result Sharp characterization of difficulty with matching sufficient and necessary conditions.

polytree structural equation model Chow-Liu algorithm CPDAG inverse correlation matrix

2021-07-22abs ↗pdf ↗

Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learningcs.LG

Novel confidence intervals improve convergence rates for sparse kernel-based models.

problem High computational cost in kernel-based learning models.

method Novel confidence intervals for Nyström method and sparse variational Gaussian process approximation.

result Improved performance bounds in regression and optimization problems.

kernel-based learning sparse approximation Nyström method Gaussian processes confidence intervals

2022-02-08abs ↗pdf ↗