BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20200129T163559Z
LOCATION:502-503-504
DTSTART;TZID=America/Denver:20191118T143000
DTEND;TZID=America/Denver:20191118T150000
UID:submissions.supercomputing.org_SC19_sess115_ws_mlhpce114@linklings.com
SUMMARY:Scalable Hyperparameter Optimization with Lazy Gaussian Processes
DESCRIPTION:Workshop\n\nScalable Hyperparameter Optimization with Lazy Gau
 ssian Processes\n\nRam, Müller, Pfreundt, Gauger, Keuper\n\nMost machine l
 earning methods require careful selection of hyper-parameters in order to 
 train a high performing model with good generalization abilities. Hence, s
 everal automatic selection algorithms have been introduced to overcome ted
 ious manual (try and error) tuning of these parameters. Due to its very hi
 gh sample efficiency, Bayesian Optimization over a Gaussian Processes mode
 ling of the parameter space has become the method of choice. Unfortunately
 , this approach suffers from a cubic compute complexity due to underlying 
 Cholesky factorization, which makes it very hard to be scaled beyond a sma
 ll number of sampling steps.\n\nIn this paper, we present a novel, highly 
 accurate approximation of the underlying Gaussian Process. Reducing its co
 mputational complexity from cubic to quadratic allows an efficient strong 
 scaling of Bayesian Optimization while outperforming the previous approach
  regarding optimization accuracy. First experiments show speedups of a fac
 tor of 162 in single node and further speed up by a factor of 5 in a paral
 lel environment.\n\nTag: Workshop Reg Pass, Machine Learning\n\nRegistrati
 on Category: Workshop Reg Pass, Machine Learning
URL:https://sc19.supercomputing.org/presentation/?id=ws_mlhpce114&sess=ses
 s115
END:VEVENT
END:VCALENDAR