BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:65656464-6637-4262-b862-316630343635
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Randomized Asymmetric Chain of LoRA - Grigory Malinovsky\, PhD
  student\, King Abdullah University
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20270314T100000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20241103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20251102T020000
RDATE:20261101T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20250309T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20260308T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:9d070f5e-2eae-4853-b63b-f980628c0ee8
DTSTAMP:20260521T090644Z
CLASS:PUBLIC
CREATED:20250704T231508Z
DESCRIPTION:Abstract: Fine-tuning has become a popular approach to adapting
  large foundational models to specific tasks. As the size of models and da
 tasets grows\, parameter-efficient fine-tuning techniques are increasingly
  important. One of the most widely used methods is Low-Rank Adaptation (Lo
 RA)\, with adaptation update expressed as the product of two low-rank matr
 ices. While LoRA was shown to possess strong performance in fine-tuning\, 
 it often under-performs when compared to full-parameter fine-tuning (FPFT)
 . Although many variants of LoRA have been extensively studied empirically
 \, their theoretical…
DTSTART;TZID=America/Vancouver:20250721T100000
DTEND;TZID=America/Vancouver:20250721T110000
LAST-MODIFIED:20250704T232404Z
LOCATION:UBC Vancouver Campus\, ICCS X836
SUMMARY:Randomized Asymmetric Chain of LoRA - Grigory Malinovsky\, PhD stud
 ent\, King Abdullah University
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/randomized-asymmetric-chain-lora-grigory-mal
 inovsky-phd-student-king-abdullah-university
END:VEVENT
END:VCALENDAR