Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Spectral bandits for smooth graph functions

About

Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this paper, we study a bandit problem where the payoffs of arms are smooth on a graph. This framework is suitable for solving online learning problems that involve graphs, such as content-based recommendation. In this problem, each item we can recommend is a node and its expected rating is similar to its neighbors. The goal is to recommend items that have high expected ratings. We aim for the algorithms where the cumulative regret with respect to the optimal policy would not scale poorly with the number of nodes. In particular, we introduce the notion of an effective dimension, which is small in real-world graphs, and propose two algorithms for solving our problem that scale linearly and sublinearly in this dimension. Our experiments on real-world content recommendation problem show that a good estimator of user preferences for thousands of items can be learned from just tens of nodes evaluations.

Michal Valko, R\'emi Munos, Branislav Kveton, Tom\'a\v{s} Koc\'ak• 2026

Related benchmarks

TaskDatasetResultRank
Contextual BanditsMovieLens 100k
Cumulative Regret256
15
Contextual BanditsOgbn-arxiv
Cumulative Regret210.8
9
Contextual BanditsMIND small
Cumulative Regret341.7
9
Contextual BanditsMovieLens 1M
Cumulative Regret245.1
9
Contextual BanditsSynthetic SBM
Cumulative Regret466.2
5
Contextual BanditsAMAZON
Cumulative Regret R(T)195
5
Contextual BanditsLastFM
Cumulative Regret282.7
5
Showing 7 of 7 rows

Other info

Follow for update