Online Convex Optimization
Graduate text in machine learning and optimization
Current version: Sept 5 2016      First version: Oct 6 2014.
A course-book that arose from lectures given at the Technion, 2010-2014. Link to a softcopy in pdf format, free of charge:
Link to a paperback:
This version was published as a survey in the Foundation and Trends series.
Please send bugs, typos, missing references or general comments to
ehazan @ cs.princeton.edu - thank you!
Not to be reproduced or distributed without the author's permission
List of errata since published version (Foundations and Trends version) is now inside arxiv version.
Contains original illustrations and artwork by Udi Aharoni
This manuscript concerns the view of optimization as a process. In many
practical applications the environment is so complex that it is infeasible to
lay a comprehensive theoretical model and use classical algorithmic theory
and mathematical optimization. It is necessary as well as beneficial to take
a robust approach: apply an optimization method that learns as one goes
along, learning from experience as more aspects of the problem are observed.
This view of optimization as a process has become prominent in varied fields
and led to some spectacular success in modeling and systems that are now
part of our daily lives.