Learning Set Functions with Limited Complementarity
DOI:
https://doi.org/10.1609/aaai.v33i01.33015749Abstract
We study PMAC-learning of real-valued set functions with limited complementarity. We prove, to our knowledge, the first nontrivial learnability result for set functions exhibiting complementarity, generalizing Balcan and Harvey’s result for submodular functions. We prove a nearly matching information theoretical lower bound on the number of samples required, complementing our learnability result. We conduct numerical simulations to show that our algorithm is likely to perform well in practice.
Downloads
Published
2019-07-17
How to Cite
Zhang, H. (2019). Learning Set Functions with Limited Complementarity. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 5749-5756. https://doi.org/10.1609/aaai.v33i01.33015749
Issue
Section
AAAI Technical Track: Machine Learning