Open AccessStructure and learning of valuation functions
Author(s) -
Vitaly Feldman,
Jan Vondrák
Publication year - 2014
Publication title -
acm sigecom exchanges
Language(s) - English
Resource type - Journals
ISSN - 1551-9031
DOI - 10.1145/2692359.2692371
Subject(s) - subadditivity , valuation (finance) , submodular set function , mathematics , computer science , mathematical optimization , discrete mathematics , economics , finance
We discuss structural results and learning algorithms for submodular and fractionally subadditive valuation functions. While learning these valuation functions over general distributions turns out to be hard, we present compact approximate representations and efficient learning algorithms for such functions over the uniform distribution.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom