General
An Efficient Synchronization Scheme for Distributed Bandits
arXiv math.IT0 views
arXiv:2611.09806v1 Announce Type: new Abstract: We study the problem of synchronizing two players in a \emph{distributed multi-armed bandit} setting. The probability of \emph{synchronization error} is analyzed by recasting synchronization as a \emph{communication problem}. Using a well-designed random coding ensemble, we derive error exponents for the maximum-likelihood decoder. We then introduce a \emph{universal decoder} that achieves the same error exponents as the optimal decoder. Finally, applying these results to distributed multi-armed bandits, we show an upper bound on the regret of our synchronization scheme.
Source：https://arxiv.org/abs/2611.09806PreviousCapacity of Generic Symmetric Distributed Linear Computation: The Geometry of RelationsNextAsymptotic Analysis of Data Deduplication Under a Constant Edit Model
Related posts
Supabase .NET DevLog #18
0dev.to OpenSource
13,000-Fold Frequency Down Conversion From 280 MHz to 21 kHz Using Mechanical Frequency Combs
0arXiv eess.SP
An Asymptotic Framework for Closed-Form Estimators from Surrogate Estimating Equations
0arXiv stat.TH
BOXBOX: Recursive Harness Self-Improvement for Long-Running Performance Optimization
0arXiv cs.SE
Graphical Analysis of Lifted Product Code Constructions
0arXiv math.IT
The Finite Difference Method, for the heat equation on Sierpi\'{n}ski simplices
0arXiv cs.NA