Enforcing and Discovering Structure in Machine Learning

TL;DR

This paper explores methods for incorporating known structures and discovering unknown structures in machine learning models to improve their speed, accuracy, and applicability to real-world problems.

Contribution

It introduces approaches for enforcing known structures and discovering new structures within learning algorithms, advancing the integration of structured knowledge in machine learning.

Findings

Structured enforcement improves model performance

Discovery methods reveal underlying data patterns

Enhanced models are more adaptable to real-world tasks

Abstract

The world is structured in countless ways. It may be prudent to enforce corresponding structural properties to a learning algorithm's solution, such as incorporating prior beliefs, natural constraints, or causal structures. Doing so may translate to faster, more accurate, and more flexible models, which may directly relate to real-world impact. In this dissertation, we consider two different research areas that concern structuring a learning algorithm's solution: when the structure is known and when it has to be discovered.