Research
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.

168,657 papers · 148 categories

Trend · papers per month

142285427569 · Jun 202019922001200920172026
48 results for causal feature selection

A new method selects robust features for ML models using causal discovery.

problem Challenges in feature selection for ML models with limited domain knowledge.
method Multidata causal feature selection using PC1 or PCMCI algorithms.
result The method improves model performance and provides interpretable drivers.

Feature selection is a crucial preprocessing step in data analytics and machine learning. Classical feature selection algorithms select features based on the correlations between predictive features and the class variable and do not attempt to capture causal relationships between them. It has been shown that the knowle…

2019-11-17abs ↗pdf ↗

Enhanced framework selects features for unbiased causal inference.

problem Unbiased estimation of causal quantities in causal inference.
method Three-stage computational framework balancing treatment and non-treatment variables.
result Significantly reduces bias and variance in estimating causal quantities.

In this paper, we aim to develop a unified view of causal and non-causal feature selection methods. The unified view will fill in the gap in the research of the relation between the two types of methods. Based on the Bayesian network framework and information theory, we first show that causal and non-causal feature sel…

2018-02-16abs ↗pdf ↗

A decision-maker must consider cofounding bias when attempting to apply machine learning prediction, and, while feature selection is widely recognized as important process in data-analysis, it could cause cofounding bias. A causal Bayesian network is a standard tool for describing causal relationships, and if relations…

2020-02-28abs ↗pdf ↗

Paper improves feature selection for predicting outcomes from observational data.

problem Feature selection for post-intervention outcome prediction from pre-intervention variables in healthcare settings.
method Extends Markov boundary concept to treatment-outcome pairs, uses observational and experimental data.
result Combining observational and experimental data improves feature selection and effect estimation.

Predictive models can be used for causal inference with feature selection.

problem Limitations of predictive models in interpreting causal relationships.
method Constrained learning process by selecting features according to Pearl's backdoor adjustment criterion.
result Causal models provide near unbiased effect estimates and better generalization.

Method estimates causal effects from incremental data, overcoming missing data challenges.

problem Estimating causal effects from non-stationary, incrementally available observational data.
method Continual Causal Effect Representation Learning
result Method achieves continual causal effect estimation without compromising original data.

Bayesian method identifies causal sets across populations without graph knowledge.

problem Transporting causal information across populations without causal graph knowledge.
method Combines observational and experimental data to identify s-admissible backdoor sets.
result Proves asymptotic convergence and corrects transportability bias in simulations.

New feature selection methods improve uplift modeling accuracy.

problem Overfitting and poor interpretability in feature selection for uplift models.
method Explicitly designed feature selection methods inspired by statistics and information theory.
result Proposed methods outperform traditional feature selection methods in uplift modeling.

Most of previous machine learning algorithms are proposed based on the i.i.d. hypothesis. However, this ideal assumption is often violated in real applications, where selection bias may arise between training and testing process. Moreover, in many scenarios, the testing data is not even available during the training pr…

2017-08-22abs ↗pdf ↗

Study finds real-world datasets contain natural experiments that can improve model performance.

problem Detecting natural experiments in real-world datasets for causal inference.
method Synthetic graph simulation and feature selection based on causal links.
result Real-world datasets contain natural experiments that can be exploited for improved model performance.

Cross-balancing improves causal inference by balancing features with outcome data.

problem Balancing features for valid causal inference when outcome data is available.
method Cross-balancing using sample splitting to separate feature construction and weight estimation errors.
result Cross-balancing produces consistent, asymptotically normal, and efficient estimators under mild conditions.

New method identifies causes in time series with latent variables.

problem Identifying direct and indirect causes in time series data with hidden variables.
method Proves necessary and sufficient conditions for causal feature selection using graph constraints and conditional independence tests.
result Method outperforms Granger causality in identifying causes with low false positives and false negatives.

Study clarifies variance of stratification estimators for causal effects.

problem Estimating average causal effects with discrete covariates.
method Combines insights from potential outcomes, causal diagrams, and structural models.
result Derives expressions for the variance of stratification estimators.

New scheme for sparse feature selection in networked data.

problem Sparse feature selection in distributed, communication-restricted networks.
method Distributed sparse linear regression and feature selection method.
result True causal features can be reliably recovered with minimal bandwidth usage.

Proposes a method for interpreting time-varying causal effect moderation in high-dimensional data.

problem Interpreting causal effect moderation in high-dimensional data with interpretability and avoiding false positives.
method Two-step method: 1) Selects a smaller model for linear causal effect moderation using Gaussian randomization, 2) Conditions on selection to construct a pivot for uniformly asymptotic semi-parametric inference.
result Consistently achieves valid coverage rates and shorter, bounded intervals in time-varying causal effect moderation.

Shapley value improves model interpretation but not causal inference.

problem Improving model interpretability without losing predictive power.
method Analyzed Shapley value in Bayesian networks, linking it to conditional independence.
result Eliminating high Shapley value variables does not harm predictive performance, but low Shapley value variables can.

Deconfounding scores improve causal effect estimation with weak overlap.

problem Poor overlap in treatment and control groups makes causal effect estimators brittle.
method Introduces feature representations that improve overlap without introducing bias.
result Deconfounding scores satisfy a zero-covariance condition that is identifiable in observed data.

Proposes a new method to find features affecting treatment effect distribution.

problem Existing methods fail to detect differences in treatment effect distribution parameters other than the mean.
method Formulates and estimates a feature importance measure that quantifies feature influence on potential outcome distribution discrepancies. Develops a feature selection algorithm to control type I error rate.
result Successfully discovers important features and outperforms existing mean-based methods.

The paper presents a method to estimate joint interventional distributions from marginal interventional data.

problem Estimating joint interventional distributions from marginal interventional data.
method The paper extends the Causal Maximum Entropy method to use interventional data and employs Lagrange duality to prove the solution lies in the exponential family.
result The method allows for causal feature selection and inference of joint interventional distributions.

Markov boundary improves tabular prediction but not as expected.

problem Improving tabular prediction using the Markov boundary.
method Evaluation on a synthetic SCM benchmark with feature counts from 40 to 1000.
result Restricting a regressor to the Markov boundary often improves prediction, but existing discovery and training pipelines do not fully exploit this.

New probabilistic approaches offer recourse recommendations even when causal models are imperfect.

problem Limited causal knowledge makes guaranteeing algorithmic recourse impossible.
method Two probabilistic approaches: Bayesian model averaging and average effect computation.
result Probabilistic approaches lead to more reliable recourse recommendations.

GCRL learns causal factors for motion forecasting, improving out-of-distribution prediction.

problem Sensitivity to out-of-distribution data in conventional supervised learning methods.
method Generative Causal Representation Learning (GCRL) leveraging causality for knowledge transfer.
result Significantly outperforms prior models on out-of-distribution prediction.

ECCIT improves conditional independence tests by calibrating for miscalibration.

problem Inaccurate frequentist guarantees in CITs, especially in small samples and misspecified models.
method Empirically Calibrated Conditional Independence Tests (ECCIT) that optimize and correct for miscalibration.
result ECCIT achieves valid FDR with higher power than existing calibration strategies.

New method deconfounds deep learning feature representations using counterfactual approach.

problem Improving model stability in deep learning models under dataset shifts.
method Adopting last layer features of DNNs trained with softmax activation for logistic regression, and applying counterfactual deconfounding.
result Counterfactual deconfounding can be applied to DNN feature representations, improving model stability.

The paper discusses selecting predictive models for causal inference, highlighting the challenges and proposing a solution.

problem Selecting the best predictive models for causal inference from a variety of machine learning models.
method The paper proposes using RextriskR ext{-risk}, flexible estimators, and splitting data to compute risks for model selection.
result The proposed method controls both outcome errors for treated and non-treated individuals, addressing the issue of model selection for causal inference.

Two novel methods identify influential features in CMABs for better reward distribution.

problem Suboptimal features degrade rewards, interpretability, and efficiency in CMABs.
method Heterogeneous Incremental Effect (HIE) and Heterogeneous Distribution Divergence (HDD) methods.
result Consistent ability to identify influential HTE features, enhancing CMAB performance.

Proposes Infomax and Domain-Independent Representations for robust causal inference.

problem Handling treatment selection bias and domain imbalance in causal inference with real-world data.
method Utilizes mutual information to learn domain-invariant representations that maximize predictive common information.
result Achieves state-of-the-art performance on causal effect inference across various data distributions.

Benchmark assesses LLMs' causal inference skills, revealing significant limitations.

problem Lack of rigorous evaluation of LLMs' causal inference capabilities.
method CausalPitfalls benchmark with structured challenges and grading rubrics.
result Significant limitations in current LLMs' statistical causal inference.

New algorithm identifies causal relationships from graphs, even with selection bias.

problem Identifying causal relationships from graphs with selection bias.
method Developed a measure-theoretic version of Pearl's causal calculus and a sound, complete identification algorithm.
result General measure-theoretic version of causal calculus allows for identification of causal relationships under selection bias.

New method uses DNN for genetic variant identification, controlling randomness and improving interpretability.

problem Challenges in interpreting deep neural networks for genetic variant identification.
method Interpretable neural network model with controlled variable selection using ensembling, knockoffs, and de-randomization.
result The proposed method leads to more discoveries compared to conventional methods.