Defense: Learning Structured and Causal Probabilistic Models for Computational Science

Speaker Name: 
Dhanya Sridhar
Speaker Title: 
PhD Candidate
Speaker Organization: 
Computer Science
Start Time: 
Tuesday, August 7, 2018 - 12:00pm
End Time: 
Tuesday, August 7, 2018 - 2:00pm
Location: 
Engineering 2, Room 280
Organizer: 
Lise Getoor

Abstract:   With today’s abundance of data, probabilistic models have an opportunity to drive fundamental research in social and biological sciences. However, unlike standard inference tasks, socio-behavioral and biological outcomes are frequently interdependent, rely on heterogenous observations, and require complex reasoning. Existing methods capture correlations and even non-linearities across relevant attributes, but fall short on handling the structure in these problems. Moreover, in both domains, experts seek new insights and knowledge, requiring techniques to discover patterns and causal relationships directly from data.

My dissertation addresses the challenges of computational science domains by developing a unified probabilistic framework that: 1) exploits useful structure in the domain to make collective inferences; 2) fuses several sources of signals; 2) discovers causal structure; 4) enables learning of complex, structured models directly from data. I validate this framework on important scientific modeling problems such as online debate and dialogue, mood and behavioral choices, interactions between drug treatments, and gene regulation. The empirical results and theoretical foundation laid in this thesis marry structured probabilistic methods with computational science tasks, prompting a promising line of research.