Enforcing and Discovering Structure in Machine Learning

2021/11/26 by Francesco Locatello, Locatello, Francesco
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and Data Classification #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2111.13693

openalex publication_date 2021/11/26 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28

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.

Related

• D'ya like DAGs? A Survey on Structure Learning and Causal Discovery
• Logic of Machine Learning
• Supervised structure learning
• Algorithmic causal structure emerging through compression
• Bridging Philosophy and Machine Learning: A Structuralist Framework for Classifying Neural Network Representations