BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Anna Golubeva (MIT)
DTSTART:20220927T183000Z
DTEND:20220927T193000Z
DTSTAMP:20260423T005740Z
UID:nhetc/45
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/nhetc/45/">O
 n the fundamental role of sparsity in machine learning</a>\nby Anna Golube
 va (MIT) as part of NHETC Seminar\n\n\nAbstract\nSparsity and neural-netwo
 rk pruning have become indispensable tools in applied machine learning to 
 alleviate the computational demands of ever larger models. While the numbe
 r of empirical works in this field has exploded in recent years\, bringing
  out a variety of pruning techniques\, finding sparse solutions at initial
 ization remains a challenge. Moreover\, a theoretical understanding of the
  very existence of sparse solutions in neural networks is lacking. In this
  talk\, I will discuss the most interesting open questions in this field a
 nd present some of our recent work combining theoretical and experimental 
 approaches to tackle them.\n
LOCATION:https://researchseminars.org/talk/nhetc/45/
END:VEVENT
END:VCALENDAR