Exploring the Relationship Between Social Choice and Machine Learning

My thesis will study the intersection of social choice and machine learning, with a focus on recent or under-explored social choice paradigms, such as liquid democracy, and how social choice and ML can benefit each other. My initial results show the idea of using ML and social choice to understand the other holds promise. An early project of mine uses deep learning to enhance social choice by creating a neural network that acts as a voting rule, able to be trained to select a winner satisfying customizable sets of axioms. More recently, I have explored the idea of using liquid democracy as a framework for ensembles for classification problems. I am particularly interested in improving the real-world applicability of existing social choice methods and understanding how they can more beneficially impact the world. Going forward, my primary tools in these goals are simulation and provable axiomatic or performance guarantees.