BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250626T234120Z
LOCATION:B308
DTSTART;TZID=America/New_York:20241121T090000
DTEND;TZID=America/New_York:20241121T100000
UID:submissions.supercomputing.org_SC24_sess398@linklings.com
SUMMARY:Sparsity and Quantization in ML
DESCRIPTION:MIXQ: Taming Dynamic Outliers in Mixed-Precision Quantization 
 by Online Prediction\n\nMixed-precision quantization has shown to be a pro
 mising method for enhancing the efficiency of LLMs. This technique boosts 
 computational efficiency by processing most values with low-precision, hig
 h-throughput compute units and maintains accuracy by processing outliers i
 n high-precision. However, d...\n\n\nYidong Chen, Chen Zhang, and Rongchao
  Dong (Tsinghua University, China); Haoyuan Zhang (Computer Network Inform
 ation Center, Chinese Academy of Sciences; Chinese Academy of Sciences); Y
 onghua Zhang (Tsinghua University, China); Zhonghua Lu (Computer Network I
 nformation Center, Chinese Academy of Sciences); and Jidong Zhai (Tsinghua
  University, China)\n---------------------\nLong Exposure: Accelerating Pa
 rameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity\n\nThe adapt
 ation of pre-trained LLMs to diverse downstream tasks through fine-tuning 
 is essential for numerous applications. However, the inefficiency of param
 eter-efficient fine-tuning (PEFT) techniques presents significant challeng
 es regarding time investments and operational costs. In this paper, w...\n
 \n\nTuowei Wang (Tsinghua University, China); Kun Li (Microsoft Research);
  Zixu Hao (Tsinghua University, China); Donglin Bai (Microsoft Research); 
 Ju Ren and Yaoxue Zhang (Tsinghua University, China); and Ting Cao and Mao
  Yang (Microsoft Research)\n\nTag: Algorithms, Artificial Intelligence/Mac
 hine Learning, Heterogeneous Computing, Performance Optimization\n\nRegist
 ration Category: Tech Program Reg Pass\n\nSession Chair: Ramakrishnan Kann
 an (Georgia Institute of Technology)
END:VEVENT
END:VCALENDAR