Multi-User Small Base Station Association via Contextual Combinatorial Volatile Bandits

Qureshi, Muhammad Anjum; Nika, Andi; Tekin, Cem

doi:10.1109/tcomm.2021.3064939

Cited by 4 publications

(2 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this case each group contains just one base arm and the group reward function is the identity mapping. This problem is significant and interesting to explore as it can be applied to the setup discussed in (Qureshi et al, 2021) which is assigning users to small base station channels (SBSCs).…”

Section: Special Case 2: Groups Are Singletonsmentioning

confidence: 99%

See 1 more Smart Citation

Contextual Combinatorial Volatile Bandits with Satisfying via Gaussian Processes

Elahi¹,

Baran²,

Öğüt³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In many real-world applications of combinatorial bandits such as content caching, rewards must be maximized while satisfying minimum service requirements. In addition, base arm availabilities vary over time, and actions need to be adapted to the situation to maximize the rewards. We propose a new bandit model called Contextual Combinatorial Volatile Bandits with Group Thresholds to address these challenges. Our model subsumes combinatorial bandits by considering super arms to be subsets of groups of base arms. We seek to maximize super arm rewards while satisfying thresholds of all base arm groups that constitute a super arm. To this end, we define a new notion of regret that merges super arm reward maximization with group reward satisfaction. To facilitate learning, we assume that the mean outcomes of base arms are samples from a Gaussian Process indexed by the context set X , and the expected reward is Lipschitz continuous in expected base arm outcomes. We propose an algorithm, called Thresholded Combinatorial Gaussian Process Upper Confidence Bounds (TCGP-UCB), that balances between maximizing cumulative reward and satisfying group reward thresholds and prove that it incurs Õ(K T γ T ) regret with high probability, where γ T is the maximum information gain associated with the set of base arm contexts that appeared in the first T rounds and K is the maximum super arm cardinality of any feasible action over all rounds. We show in experiments that our algorithm accumulates a reward comparable with that of the state-of-the-art combinatorial bandit algorithm while picking actions whose groups satisfy their thresholds.

show abstract

Section: Special Case 2: Groups Are Singletonsmentioning

confidence: 99%

“…These are further discussed in Section 2.8. Our setup is applicable to content caching (Müller et al, 2017), fast mmWave beam alignment problem (Wu et al, 2019), worker allocation to gem mines (Verstraeten et al, 2020) and user-small base station channel allocations (Qureshi et al, 2021).…”

Section: Introductionmentioning

confidence: 99%