Date of Award

Winter 12-2017

Embargo Period

1-25-2019

Degree Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Machine Learning

Advisor(s)

Cosma R. Shalizi

Abstract

To better understand why machine learning works, we cast learning problems as searches and characterize what makes searches successful. We prove that any search algorithm can only perform well on a narrow subset of problems, and show the effects of dependence on raising the probability of success for searches. We examine two popular ways of understanding what makes machine learning work, empirical risk minimization and compression, and show how they fit within our search frame-work. Leveraging the “dependence-first” view of learning, we apply this knowledge to areas of unsupervised time-series segmentation and automated hyperparameter optimization, developing new algorithms with strong empirical performance on real-world problem classes.

Available for download on Friday, January 25, 2019

Share

COinS