BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//LANS Seminar - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:LANS Seminar
X-ORIGINAL-URL:https://wordpress.cels.anl.gov/lans-seminars
X-WR-CALDESC:Events for LANS Seminar
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20240310T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20241103T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20250309T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20251102T070000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:20260308T080000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:20261101T070000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Chicago:20250501T110000
DTEND;TZID=America/Chicago:20250501T120000
DTSTAMP:20260610T234745
CREATED:20250424T194915Z
LAST-MODIFIED:20250425T165052Z
UID:3751-1746097200-1746100800@wordpress.cels.anl.gov
SUMMARY:LANS Seminar
DESCRIPTION:Seminar Title: Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity \nSpeaker: Kaja Gruntkowska\, PhD Student\, Optimization\, Machine Learning\, KAUST \nDate/Time: Thursday\, May 1\, 2025/ 11:00AM – 12:00 PM (Virtual)\nLocation: See Meeting URL on the cels-seminars website which will require an Argonne login. \nHost: Krishnan Raghavan \nDescription: Effective communication between the server and workers plays a key role in distributed optimization. In this paper\, we focus on optimizing the server-to-worker communication\, uncovering inefficiencies in prevalent downlink compression approaches. Considering first the pure setup where the uplink communication costs are negligible\, we introduce MARINA-P\, a novel method for downlink compression\, employing a collection of correlated compressors. Theoretical analysis demonstrates that MARINA-P with permutation compressors can achieve a server-to-worker communication complexity improving with the number of workers\, thus being provably superior to existing algorithms. We further show that MARINA-P can serve as a starting point for extensions such as methods supporting bidirectional compression. We introduce M3\, a method combining MARINA-P with uplink compression and a momentum step\, achieving bidirectional compression with provable improvements in total communication complexity as the number of workers increases. Theoretical findings align closely with empirical experiments\, underscoring the efficiency of the proposed algorithms. \nBio: Kaja Gruntkowska is a PhD student in Optimization for Machine Learning at KAUST\, advised by Prof. Peter Richtárik. Her research focuses on developing the algorithmic and mathematical foundations of randomized optimization\, with a particular emphasis on distributed computing. She works on designing practically motivated algorithms with provable convergence guarantees\, bridging theory and real-world applications to advance scalable machine learning. She completed her Bachelor’s in Mathematics and Statistics at the University of Warwick and earned a Master’s in Statistical Science from the University of Oxford. \nPlease note that the meeting URL for this event can be seen on the cels-seminars website which requires an Argonne login. \n\nSee all upcoming talks at https://www.anl.gov/mcs/lans-seminars
URL:https://wordpress.cels.anl.gov/lans-seminars/event/3751/
LOCATION:https://wordpress.cels.anl.gov/cels-seminars/event/lans-seminar-179/
CATEGORIES:Seminar
END:VEVENT
END:VCALENDAR