Fast and Accurate Ranking Regression
[edit]
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:7788, 2020.
Abstract
We consider a ranking regression problem in which we use a dataset of ranked choices to learn PlackettLuce scores as functions of sample features. We solve the maximum likelihood estimation problem by using the Alternating Directions Method of Multipliers (ADMM), effectively separating the learning of scores and model parameters. This separation allows us to express scores as the stationary distribution of a continuoustime Markov Chain. Using this equivalence, we propose two spectral algorithms for ranking regression that learn model parameters up to 579 times faster than the Newton’s method.
Related Material


