Loading…
This event has ended. View the official site or create your own event → Check it out
This event has ended. Create your own
View analytic
Tuesday, December 8 • 19:00 - 23:59
Combinatorial Bandits Revisited

Sign up or log in to save this to your schedule and see who's attending!

This paper investigates stochastic and adversarial combinatorial multi-armed bandit problems. In the stochastic setting under semi-bandit feedback, we derive a problem-specific regret lower bound, and discuss its scaling with the dimension of the decision space. We propose ESCB, an algorithm that efficiently exploits the structure of the problem and provide a finite-time analysis of its regret. ESCB has better performance guarantees than existing algorithms, and significantly outperforms these algorithms in practice. In the adversarial setting under bandit feedback, we propose CombEXP, an algorithm with the same regret scaling as state-of-the-art algorithms, but with lower computational complexity for some combinatorial problems.


Tuesday December 8, 2015 19:00 - 23:59
210 C #96