A Vrbo team used daily Thompson sampling to rank four recommendation models by click-through rate, but the A/B validation they report is for a previous campaign's winner, not the current one.
On the Optimality of Perturbations in Stochastic and Adversarial Multi-armed Bandit Problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We investigate the optimality of perturbation based algorithms in the stochastic and adversarial multi-armed bandit problems. For the stochastic case, we provide a unified regret analysis for both sub-Weibull and bounded perturbations when rewards are sub-Gaussian. Our bounds are instance optimal for sub-Weibull perturbations with parameter 2 that also have a matching lower tail bound, and all bounded support perturbations where there is sufficient probability mass at the extremes of the support. For the adversarial setting, we prove rigorous barriers against two natural solution approaches using tools from discrete choice theory and extreme value theory. Our results suggest that the optimal perturbation, if it exists, will be of Frechet-type.
fields
cs.IR 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Accelerated learning from recommender systems using multi-armed bandit
A Vrbo team used daily Thompson sampling to rank four recommendation models by click-through rate, but the A/B validation they report is for a previous campaign's winner, not the current one.