Early notification is possible for early submissions upon request.
Topics of interest in this workshop include but are not limited to:
● Implicit and explicit regularization, and the role of optimization algorithms in generalization
● Architecture choices that improve generalization
● Empirical approaches to understanding generalization
● Generalization bounds and empirical criteria to evaluate generalization bounds
● Robustness: generalizing to distributional shift a.k.a dataset shift
● Generalization in the context of representation/unsupervised learning, transfer learning and reinforcement learning: definitions and empirical approaches
Submissions will be accepted as posters and (or) spotlight presentations.
Submissions must be made through workshop's EasyChair page. All submissions must be in ICML's official PDF format, except using icmlw2019generalization.sty instead of the original style file (icml2019.sty). The submission length is limited to at most 4 pages, excluding references. The submissions may include an optional supplementary appendix. The submissions should follow double blind policy and not published before under peer reviewed conferences. Questions can be sent to {hmobahi,dilipkay,bneyshabur}@X.com where x=gmail.