litlas
ログインアカウント作成

Local Causal and Markov Blanket Induction for Causal Discovery and Feature Selection for Classification Part I: Algorithms and Empirical Evaluation

著者: Constantin F. Aliferis, Alexander R. Statnikov, Ioannis Tsamardinos, Subramani Mani, Xenofon D. Koutsoukos - Journal of Machine Learning Research, JMLR 2010 被引用: 490

In part I of this work we introduced and evaluated the Generalized Local Learning (GLL) framework for producing local causal and Markov blanket induction algorithms. In the present second part we analyze the behavior of GLL algorithms and provide extensions to the core methods. Specifically, we investigate the empirical convergence of GLL to the true local neighborhood as a function of sample size. Moreover, we study how predictivity improves with increasing sample size. Then we investigate how sensitive are the algorithms to multiple statistical testing, especially in the presence of many irrelevant features. Next we discuss the role of the algorithm parameters and also show that Markov blanket and causal graph concepts can be used to understand deviations from optimality of state-of-the-art non-causal algorithms. The present paper also introduces the following extensions to the core GLL framework: parallel and distributed versions of GLL algorithms, versions with false discovery rate control, strategies for constructing novel heuristics for specific domains, and divide-and-conquer local-to-global learning (LGL) strategies. We test the

Bayesian NetworkInduction via Local…Bayesian Network Induction via Local NeighborhoodsHITON: A Novel MarkovBlanket Algorithm for…HITON: A Novel Markov Blanket Algorithm for Optimal Variable SelectionTime and sampleefficient discovery of…Time and sample efficient discovery of Markov blankets and direct causal relationsAlgorithms for LargeScale Markov Blanket…Algorithms for Large Scale Markov Blanket DiscoveryCausal Explorer: ACausal Probabilistic…Causal Explorer: A Causal Probabilistic Network Learning Toolkit for Biomedical DiscoveryTowards PrincipledFeature Selection…Towards Principled Feature Selection: Relevancy, Filters and WrappersCausal Discovery Using ABayesian Local Causal…Causal Discovery Using A Bayesian Local Causal Discovery AlgorithmSpeculative MarkovBlanket Discovery for…Speculative Markov Blanket Discovery for Optimal Feature SelectionGEMS: A system forautomated cancer…GEMS: A system for automated cancer diagnosis and biomarker discovery from microarray gene expression dataTowards scalable anddata efficient learning…Towards scalable and data efficient learning of Markov boundariesThe max-minhill-climbing Bayesian…The max-min hill-climbing Bayesian network structure learning algorithmLocal Causal and MarkovBlanket Induction for…Local Causal and Markov Blanket Induction for Causal Discovery and Feature Selection for Classification Part II: Analysis and ExtensionsFeature subset selectionwith cumulate…Feature subset selection with cumulate conditional mutual information minimizationAlgorithms for Discoveryof Multiple Markov…Algorithms for Discovery of Multiple Markov Boundaries.Profit optimizingcustomer churn…Profit optimizing customer churn prediction with Bayesian network classifiersUltra-scalable andefficient methods for…Ultra-scalable and efficient methods for hybrid observational and experimental local causal pathway discoveryEfficient Markov BlanketDiscovery and Its…Efficient Markov Blanket Discovery and Its ApplicationSwamping and masking inMarkov boundary…Swamping and masking in Markov boundary discoveryMarkov Blanket FeatureSelection Using…Markov Blanket Feature Selection Using Representative SetsLocal-to-Global BayesianNetwork Structure…Local-to-Global Bayesian Network Structure LearningMining Markov BlanketsWithout Causal…Mining Markov Blankets Without Causal SufficiencyMarkov Blanket andMarkov Boundary of…Markov Blanket and Markov Boundary of Multiple VariablesLearning Markov BlanketsFrom Multiple…Learning Markov Blankets From Multiple Interventional Data SetsMulti-label CausalVariable Discovery…Multi-label Causal Variable Discovery: Learning Common Causal Variables and Label-specific Causal VariablesLocal Causal and MarkovBlanket Induction for…Local Causal and Markov Blanket Induction for Causal Discovery and Feature Selection for Classification Part I: Algorithms and Empirical Evaluation過去の参考文献中心の論文この論文を引用する論文古い新しい

ノードをクリックするとフォーカスを固定、空白をクリックすると本論文に戻ります。ホバーで一時的にプレビューできます。各ノードのページはタイトルから開けます。