Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

67 Citations (Scopus)

Fingerprint

Dive into the research topics of 'Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training'. Together they form a unique fingerprint.

Computer Science

Neuroscience