Timezone: »

TopRank: A practical algorithm for online stochastic ranking
Tor Lattimore · Branislav Kveton · Shuai Li · Csaba Szepesvari

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #149

Online learning to rank is a sequential decision-making problem where in each round the learning agent chooses a list of items and receives feedback in the form of clicks from the user. Many sample-efficient algorithms have been proposed for this problem that assume a specific click model connecting rankings and user behavior. We propose a generalized click model that encompasses many existing models, including the position-based and cascade models. Our generalization motivates a novel online learning algorithm based on topological sort, which we call TopRank. TopRank is (a) more natural than existing algorithms, (b) has stronger regret guarantees than existing algorithms with comparable generality, (c) has a more insightful proof that leaves the door open to many generalizations, (d) outperforms existing algorithms empirically.

Author Information

Tor Lattimore (DeepMind)
Branislav Kveton (Google)
Shuai Li (The Chinese University of Hong Kong)
Csaba Szepesvari (University of Alberta)

More from the Same Authors