=Paper=
{{Paper
|id=Vol-1378/amw_keynote4
|storemode=property
|title=Symmetry in Probabilistic Databases
|pdfUrl=https://ceur-ws.org/Vol-1378/amw_keynote4.pdf
|volume=Vol-1378
|dblpUrl=https://dblp.org/rec/conf/amw/Broeck15
}}
==Symmetry in Probabilistic Databases==
<pdf width="1500px">https://ceur-ws.org/Vol-1378/amw_keynote4.pdf</pdf>
<pre>
   Symmetry in Probabilistic Databases

                         Guy Van den Broeck

 Computer Science Department University of California, Los Angeles
                      guyvdb@cs.ucla.edu



Abstract. Researchers in databases, AI, and machine learning, have
all proposed representations of probability distributions over relational
databases (possible worlds). In a tuple-independent probabilistic database,
the possible worlds all have distinct probabilities, because the tuple prob-
abilities are distinct. In AI and machine learning, however, one typically
learns highly symmetric distributions, where large numbers of symmetric
databases get assigned identical probability. This symmetry helps with
generalizing from data. In this talk I discuss what happens to standard
database notions of data and combined complexity when considering AI-
style symmetric probabilistic databases. The question proves to be a fer-
tile ground for database theory, with interesting connections to counting
complexity and 0-1 laws.

</pre>