A contextual dueling bandit algorithm asks users to compare each new item against a past item for free, achieving O(sqrt(T)) regret after a short random exploration phase.
Improved algorithms for linear stochastic bandits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Recycling History: Efficient Recommendations from Contextual Dueling Bandits
A contextual dueling bandit algorithm asks users to compare each new item against a past item for free, achieving O(sqrt(T)) regret after a short random exploration phase.