Learning Tree Structured Potential Games
Name
6152-learning-tree-structured-potential-games.pdf
Description
Published version
Size
374.18 KB
Format
Unknown
Checksum (MD5)
9dfd61bb7ca7690a5377265515fe2830
Author(s)
Garg, Vikas K.
Jaakkola, Tommi
Date Issued
2016
Citation
Garg, Vikas K. and Jaakkola, Tommi. 2016. "Learning Tree Structured Potential Games."
Version
Final published version
Abstract
© 2016 NIPS Foundation - All Rights Reserved. Many real phenomena, including behaviors, involve strategic interactions that can be learned from data. We focus on learning tree structured potential games where equilibria are represented by local maxima of an underlying potential function. We cast the learning problem within a max margin setting and show that the problem is NP-hard even when the strategic interactions form a tree. We develop a variant of dual decomposition to estimate the underlying game and demonstrate with synthetic and real decision/voting data that the game theoretic perspective (carving out local maxima) enables meaningful recovery.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
