Title: Comparison-Based Learning with Rank Nets

Authors: Amin Karbasi, Stratis Ioannidis, Laurent Massoulié:


We consider the problem of search through comparisons, where a user is presented with two candidate objects and reveals which is closer to her intended target. We study adap- tive strategies for finding the target, that require knowledge of rank relationships but not actual distances between objects. We propose a new strategy based on rank nets, and show that for target distributions with a bounded doubling constant, it finds the tar- get in a number of comparisons close to the entropy of the target distribution and, hence, of the optimum. We extend these results to the case of noisy oracles, and compare this strategy to prior art over multiple datasets.

Full Text: [PDF]

Accessibility at Yale   Inference, Information, and Decision Group at Yale