Combining Sources and Leveraging Contexts

Author: Mazaheri, Bijan Henrik Socrates

Year: 2024

Degree: Dissertation (Ph.D.)

Advisors: Bruck, Jehoshua; Schulman, Leonard J.

Committee Members: Eberhardt, Frederick D.; Janzing, Dominik; Rabani, Yuval; Bruck, Jehoshua; Schulman, Leonard J.

Option: Computing and Mathematical Sciences

DOI: 10.7907/7t4d-xg91

Abstract

In this thesis we discuss two levels of knowledge beyond regression and classification. The first involves the identification of exchangeable scenarios or individuals from which causal relationships can be ascertained. We discuss one key difficulty of this task, the "Multi-Source Conundrum," which emerges whenever data is merged from multiple sources. This motivates the "Principle of Limited Latent Classes," an assumption which allows us to introduce new algorithms for deconfounding and causal structure learning.

The second level of knowledge involves the expansion from contextual exchangeability to contextual synthesis. We will study a paradox of nontransitivity that occurs when combining multiple contexts, as well a demonstrating robustness gains from using context-dependent counterfactuals as training features. Through these points, we present contextual synthesis as a new frontier with promise for advances in out-of-distribution robustness, fairness, and privacy.

Files