Filter by

  • Publication Year
  • Availability
  • Attachment
  • Collection Type
  • General Material Designation
    See More
  • Location
  • Language
Found 1 from your keywords: author="Tarlow, Daniel,"
cover
Perturbations optimization and statistics
Comment Share
M.I.T. Press,Hazan, Tamir,Papandreou, George,Tarlow, Daniel,

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 always the best strategy, even when learning in a supervised learning setting. An emerging body of wo…

Edition
-
ISBN/ISSN
9780262337939
Collation
1 online resource (ix, 401 pages).
Series Title
-
Call Number
-