A Note on Bounding Regret of the C$^2$UCB Contextual Combinatorial Bandit

Oetomo, Bastian; Perera, Malinga; Borovica-Gajić, Renata; Rubinstein, Benjamin I. P.

doi:10.48550/arxiv.1902.07500

Cited by 1 publication

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When g is assumed to be monotonic and Lipschitz continuous, [26] claimed that C 2 UCB enjoys Õ( √ T ) α-regret. 2 We have corrected an error in the original proof, as seen in our technical note [28], confirming the Õ( √ T ) α-regret. This expression is sub-linear in T , implying that the per-round average cumulative regret approaches zero after sufficiently many rounds.…”

Section: Contextual Combinatorial Banditsmentioning

confidence: 58%

DBA bandits: Self-driving index tuning under ad-hoc, analytical workloads with safety guarantees

Perera¹,

Oetomo²,

Rubinstein³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Automating physical database design has remained a long-term interest in database research due to substantial performance gains afforded by optimised structures. Despite significant progress, a majority of today's commercial solutions are highly manual, requiring offline invocation by database administrators (DBAs) who are expected to identify and supply representative training workloads. Even the latest advancements like query stores provide only limited support for dynamic environments. This status quo is untenable: identifying representative static workloads is no longer realistic; and physical design tools remain susceptible to the query optimiser's cost misestimates (stemming from unrealistic assumptions such as attribute value independence and uniformity of data distribution).We propose a self-driving approach to online index selection that eschews the DBA and query optimiser, and instead learns the benefits of viable structures through strategic exploration and direct performance observation. We view the problem as one of sequential decision making under uncertainty, specifically within the bandit learning setting. Multi-armed bandits balance exploration and exploitation to provably guarantee average performance that converges to a fixed policy that is optimal with perfect hindsight. Our comprehensive empirical results demonstrate up to 75% speed-up on shifting and ad-hoc workloads and 28% speed-up on static workloads compared against a state-ofthe-art commercial tuning tool.

show abstract

Section: Contextual Combinatorial Banditsmentioning

confidence: 58%