Perturbations, optimization, and statistics /

A description of perturbation-based methods developed in machine learning to augment novel optimization methods with strong statistical guarantees.In nearly all machine learning, decisions must be made given current knowledge. Surprisingly, making what is believed to be the best decision is not alwa...

Full description

Bibliographic Details

Other Authors:	Hazan, Tamir (Editor), Papandreou, George (Editor), Tarlow, Daniel (Editor)
Format:	eBook
Language:	English
Published:	Cambridge, Massachusetts : The MIT Press, [2017]
Series:	Neural information processing series
Subjects:	Machine learning. Perturbation (Mathematics) Mathematical optimization. COMPUTER SCIENCE/General COMPUTER SCIENCE/Machine Learning & Neural Networks Electronic books.
Online Access:	Connect to the full text of this electronic book