Cost-aware Cascading Bandits

Zhou, Ruida; Gan, Chao; Yan, Jiayong; Shen, Cong

doi:10.48550/arxiv.1805.08638

Cited by 3 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our BaTT algorithm is motivated by recent advances in multi-armed bandits. Its problem formulation is inspired by the cascading bandit (Kveton et al 2015;Zhou et al 2018), which returns a list of arms to pull. The cost-aware cascading bandit considers a known cost of pulling each arm (Zhou et al 2018) and is used for handover management (Wang et al 2020).…”

Section: Related Workmentioning

confidence: 99%

“…Its problem formulation is inspired by the cascading bandit (Kveton et al 2015;Zhou et al 2018), which returns a list of arms to pull. The cost-aware cascading bandit considers a known cost of pulling each arm (Zhou et al 2018) and is used for handover management (Wang et al 2020). Our problem differs from these because our evaluation is based on real-traces and does not assume a known cost.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Bandit Policies for Reliable Cellular Network Handovers in Extreme Mobility

Li,

Datta,

Ding

et al. 2020

Preprint

View full text Add to dashboard Cite

The demand for seamless Internet access under extreme user mobility, such as on high-speed trains and vehicles, has become a norm rather than an exception. However, the 4G/5G mobile network is not always reliable to meet this demand, with non-negligible failures during the handover between base stations. A fundamental challenge of reliability is to balance the exploration of more measurements for satisfactory handover, and exploitation for timely handover (before the fast-moving user leaves the serving base station's radio coverage). This paper formulates this trade-off in extreme mobility as a composition of two distinct multi-armed bandit problems. We propose Bandit and Threshold Tuning (BaTT) to minimize the regret of handover failures in extreme mobility. BaTT uses -binary-search to optimize the threshold of the serving cell's signal strength to initiate the handover procedure with O(log J log T ) regret. It further devises opportunistic Thompson sampling, which optimizes the sequence of the target cells to measure for reliable handover with O(log T ) regret. Our experiment over a real LTE dataset from Chinese high-speed rails validates significant regret reduction and a 29.1% handover failure reduction.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Bandit Policies for Reliable Cellular Network Handovers in Extreme Mobility

Li,

Datta,

Ding

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

Observe Before Play: Multi-armed Bandit with Pre-observations

Zuo

Zhang

Joe‐Wong

2019

Preprint

View full text Add to dashboard Cite

On Learning to Rank Long Sequences with Contextual Bandits

Santara¹,

Gentile²,

Aggarwal³

et al. 2021

Preprint

View full text Add to dashboard Cite

Motivated by problems of learning to rank long item sequences, we introduce a variant of the cascading bandit model that considers flexible length sequences with varying rewards and losses. We formulate two generative models for this problem within the generalized linear setting, and design and analyze upper confidence algorithms for it. Our analysis delivers tight regret bounds which, when specialized to vanilla cascading bandits, results in sharper guarantees than previously available in the literature. We evaluate our algorithms on a number of real-world datasets, and show significantly improved empirical performance as compared to known cascading bandit baselines.

show abstract

Cost-aware Cascading Bandits

Cited by 3 publications

References 2 publications

Bandit Policies for Reliable Cellular Network Handovers in Extreme Mobility

Bandit Policies for Reliable Cellular Network Handovers in Extreme Mobility

Observe Before Play: Multi-armed Bandit with Pre-observations

On Learning to Rank Long Sequences with Contextual Bandits

Contact Info

Product

Resources

About