Sanghack Lee - Academia.edu (original) (raw)
Related Authors
Università degli Studi del Piemonte Orientale "Amedeo Avogadro"
Uploads
Papers by Sanghack Lee
Uncertainty in Artificial Intelligence, 2013
We introduce z-transportability, the problem of estimating the causal eect of a set of vari- able... more We introduce z-transportability, the problem of estimating the causal eect of a set of vari- ables X on another set of variables Y in a target domain from experiments on any sub- set of controllable variables Z where Z is an arbitrary subset of observable variables V in a source domain. z-Transportability general- izes z-identiability, the problem of estimat- ing
National Conference on Artificial Intelligence, 2013
We study m-transportability, a generalization of transporta- bility, which offers a license to us... more We study m-transportability, a generalization of transporta- bility, which offers a license to use causal information elicited from experiments and observations in m 1 source en- vironments to estimate a causal effect in a given target environment. We provide a novel characterization of m- transportability that directly exploits the completeness of do- calculus to obtain the necessary and sufficient conditions
Many big data applications give rise to distri- butional data wherein objects or individuals are ... more Many big data applications give rise to distri- butional data wherein objects or individuals are naturally represented as K-tuples of bags of feature values where feature values in each bag are sampled from a feature and object specific distribution. We formulate and solve the problem of learning classifiers from distributional data. We consider three classes of methods for learning distributional
Workshop on Advances in Causal Inference, Conference on Uncertainty in Artificial Intelligence, 2015
Maier et al. (2010) introduced the relational causal model (RCM) for representing and inferring c... more Maier et al. (2010) introduced the relational causal model (RCM) for representing and inferring causal relationships in relational data. A lifted representation, called abstract ground graph (AGG), plays a central role in reasoning with and learning of RCM. The correctness of the algorithm proposed by Maier et al. (2013) for learning RCM from data relies on the soundness and completeness of AGG for relational d-separation to reduce the learning of an RCM to learning of an AGG. We revisit the definition of AGG and show that AGG, as defined in Maieret al. (2013), does not correctly abstract all ground graphs. We revise the definition of AGG to ensure that it correctly abstracts all ground graphs. We further show that AGG representation is not complete for relational d-separation, that is, there can exist conditional independence relations in an RCM that are not entailed by AGG. A careful examination of the relationship between the lack of completeness of AGG for relational d-separation and faithfulness conditions suggests that weaker notions of completeness, namely adjacency faithfulness and orientation faithfulness between an RCM and its AGG, can be used to learn an RCM from data.
Uncertainty in Artificial Intelligence, 2013
We introduce z-transportability, the problem of estimating the causal eect of a set of vari- able... more We introduce z-transportability, the problem of estimating the causal eect of a set of vari- ables X on another set of variables Y in a target domain from experiments on any sub- set of controllable variables Z where Z is an arbitrary subset of observable variables V in a source domain. z-Transportability general- izes z-identiability, the problem of estimat- ing
National Conference on Artificial Intelligence, 2013
We study m-transportability, a generalization of transporta- bility, which offers a license to us... more We study m-transportability, a generalization of transporta- bility, which offers a license to use causal information elicited from experiments and observations in m 1 source en- vironments to estimate a causal effect in a given target environment. We provide a novel characterization of m- transportability that directly exploits the completeness of do- calculus to obtain the necessary and sufficient conditions
Many big data applications give rise to distri- butional data wherein objects or individuals are ... more Many big data applications give rise to distri- butional data wherein objects or individuals are naturally represented as K-tuples of bags of feature values where feature values in each bag are sampled from a feature and object specific distribution. We formulate and solve the problem of learning classifiers from distributional data. We consider three classes of methods for learning distributional
Workshop on Advances in Causal Inference, Conference on Uncertainty in Artificial Intelligence, 2015
Maier et al. (2010) introduced the relational causal model (RCM) for representing and inferring c... more Maier et al. (2010) introduced the relational causal model (RCM) for representing and inferring causal relationships in relational data. A lifted representation, called abstract ground graph (AGG), plays a central role in reasoning with and learning of RCM. The correctness of the algorithm proposed by Maier et al. (2013) for learning RCM from data relies on the soundness and completeness of AGG for relational d-separation to reduce the learning of an RCM to learning of an AGG. We revisit the definition of AGG and show that AGG, as defined in Maieret al. (2013), does not correctly abstract all ground graphs. We revise the definition of AGG to ensure that it correctly abstracts all ground graphs. We further show that AGG representation is not complete for relational d-separation, that is, there can exist conditional independence relations in an RCM that are not entailed by AGG. A careful examination of the relationship between the lack of completeness of AGG for relational d-separation and faithfulness conditions suggests that weaker notions of completeness, namely adjacency faithfulness and orientation faithfulness between an RCM and its AGG, can be used to learn an RCM from data.