Machine Learning, Optimization, and Anti-Training with Sacrificial Data
Traditionally the machine learning community has viewed the No Free Lunch (NFL) theorems for search and optimization as a limitation. I review, analyze, and unify the NFL theorem with the many frameworks to arrive at necessary conditions for improving black-box optimization, model selection, and mac...
| Main Author: | |
|---|---|
| Other Authors: | |
| Language: | en_US |
| Published: |
The University of Arizona.
2016
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10150/605111 http://arizona.openrepository.com/arizona/handle/10150/605111 |