This event is a valuable opportunity to gain insights into Artificial Intelligence and Machine Learning through the lens of causality and to connect with Prof. Valtorta, who is widely respected in the field.
Date: Friday, October 20, 2023
Time: 2:00 pm
Location: Room 325 Anne Belk Hall
Title: Causal Bayesian Networks and Some Related Identifiability Results
Abstract: A causal Bayesian network is a pair consisting of a directed acyclic graph (called a causal graph) that represents causal relationships and a set of probability tables, that together with the graph specify the joint probability of the variables represented as nodes in the graph. We describe the probabilistic semantics of causality proposed by Pearl for this graphical probabilistic model, and how unobservable variables greatly complicate models and their application. A common question about causal Bayesian networks is the problem of identifying causal effects from nonexperimental data, which is called the identifiability problem. In the basic version of this problem, a semi-empirical scientist postulates a set of causal mechanisms and uses them, together with a probability distribution on the observable set of variables in a domain, to predict the effect of a manipulation on some variable(s) of interest. We explain this problem, provide several examples, and describe a sound and complete calculus to compute causal effects.
Bio: Marco Valtorta (Laurea, Politecnico di Milano, 1980; Ph.D., Duke University, 1987) has been a professor of Computer Science and Engineering at the University of South Carolina since 1988. He is mainly interested in the area of uncertainty in artificial intelligence; his earlier work was in heuristic search and knowledge refinement. As of October 2023, he has graduated 12 Ph.D. and 24 M.S. students. He was chair of the university tenure and promotion committee and, from 2017-2019, chair of the university faculty senate. His CV is available at https://cse.sc.edu/~mgv/CV.pdf.