Spectral bandit algorithms for graph-smooth payoffs achieve regret linear or sublinear in an effective dimension that is small on real graphs, allowing preference learning from tens of evaluations on thousands of items.
Semi-Supervised Learning Literature Survey
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spectral bandits for smooth graph functions
Spectral bandit algorithms for graph-smooth payoffs achieve regret linear or sublinear in an effective dimension that is small on real graphs, allowing preference learning from tens of evaluations on thousands of items.