Timezone: »

Submodular Hamming Metrics
Jennifer Gillenwater · Rishabh K Iyer · Bethany Lusch · Rahul Kidambi · Jeff Bilmes

Tue Dec 08 07:10 AM -- 07:35 AM (PST) @ Room 210 A

We show that there is a largely unexplored class of functions (positive polymatroids) that can define proper discrete metrics over pairs of binary vectors and that are fairly tractable to optimize over. By exploiting submodularity, we are able to give hardness results and approximation algorithms for optimizing over such metrics. Additionally, we demonstrate empirically the effectiveness of these metrics and associated algorithms on both a metric minimization task (a form of clustering) and also a metric maximization task (generating diverse k-best lists).

Author Information

Jennifer Gillenwater (University of Washington)
Rishabh K Iyer (University of Washington, Seattle)
Bethany Lusch (University of Washington)
Rahul Kidambi (University of Washington)
Jeff Bilmes (University of Washington, Seattle)

More from the Same Authors