BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//prima-2022//speaker calendar//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZOME
TZID:America/Vancouver
TZURL:http://tzurl.org/zoneinfo-outlook/America/Vancouver
X-LIC-LOCATION:America/Vancouver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP;TZID=America/Vancouver:20221208T163000
DTSTART;TZID=America/Vancouver:20221208T163000
DTEND;TZID=America/Vancouver:20221208T165500

UID:20221208T163000@prima2022.primamath.org
SUMMARY:Post-training Quantization for Deep Neural Networks with Provable Guarantees
DESCRIPTION:Quantization is one of the compression techniques to reduce computation cost, memory, and power consumption of deep neural networks (DNNs). In this talk, we will focus on a post-training quantization algorithm, GPFQ, that is based on a deterministic greedy path-following mechanism, and its stochastic variant SGPFQ. In both cases, we rigorously analyze the associated error bounds for quantization and show that for quantizing a single-layer network, the relative square error essentially decays linearly in the number of weights -- i.e., level of over-parametrization. To empirically evaluate the method, we quantize several common DNN architectures with few bits per weight, and test them on ImageNet, showing only minor loss of accuracy compared to unquantized models.
STATUS:CONFIRMED
LOCATION:Junior Ballroom C
END:VEVENT
END:VCALENDAR