1216_Montanez_2017_2019.pdf (1.77 MB)
Why Machine Learning Works
thesis
posted on 2017-12-01, 00:00 authored by George D. MontanezTo 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.
History
Date
2017-12-01Degree Type
- Dissertation
Department
- Machine Learning
Degree Name
- Doctor of Philosophy (PhD)