BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-berlin-2023//talk//JZSYA3
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-berlin-2023-JZSYA3@pretalx.com
DTSTART;TZID=CET:20230418T131500
DTEND;TZID=CET:20230418T140000
DESCRIPTION:Database Management Systems (DBMSs) are the backbone for managi
 ng large volumes of data efficiently and thus play a central role in busin
 ess and science today. For providing high performance\, many of the most c
 omplex DBMS components such as query optimizers or schedulers involve solv
 ing non-trivial problems. To tackle such problems\, very recent work has o
 utlined a new direction of so-called learned DBMSs where core parts of DBM
 Ss are being replaced by machine learning (ML) models which has shown to p
 rovide significant performance benefits. However\, a major drawback of the
  current approaches to enabling learned DBMS components is that they not o
 nly cause very high overhead for training an ML model to replace a DBMS co
 mponent but that the overhead occurs repeatedly which renders these approa
 ches far from practical. Hence\, in this talk\, I present my vision of Lea
 rned DBMS Components 2.0 to tackle these issues. First\, I will introduce 
 data-driven learning where the idea is to learn the data distribution over
  a complex relational schema. In contrast to workload-driven learning\, no
  large workload has to be executed on the database to gather training data
 . While data-driven learning has many applications such as cardinality est
 imation or approximate query processing\, many DBMS tasks such as physical
  cost estimation cannot be supported. I thus propose a second technique ca
 lled zero-shot learning which is a general paradigm for learned DBMS compo
 nents. Here\, the idea is to train model
DTSTAMP:20260718T150330Z
LOCATION:Kuppelsaal
SUMMARY:Keynote - Towards Learned Database Systems - Carsten Binnig
URL:https://pretalx.com/pyconde-pydata-berlin-2023/talk/JZSYA3/
END:VEVENT
END:VCALENDAR