acm-header
Sign In

Communications of the ACM

Latest Research


Latest Research Research Archive Refine your search:
dateMore Than a Year Ago
subjectTheory
author Moritz Hardt

Understanding Deep Learning (Still) Requires Rethinking Generalization
From Communications of the ACM

Understanding Deep Learning (Still) Requires Rethinking Generalization

In this work, we presented a simple experimental framework for interrogating purported measures of generalization.

Guilt-Free Data Reuse
From Communications of the ACM

Guilt-Free Data Reuse

In this work, we initiate a principled study of how to guarantee the validity of statistical inference in adaptive data analysis.
Sign In for Full Access
» Forgot Password? » Create an ACM Web Account