PulseAugur
LIVE 01:43:03
research · [2 sources] ·
0
research

Federated bandits algorithm slashes computation and communication costs via sketching

Researchers have developed a new method called Federated Sketch Contextual Linear Bandits (FSCLB) to address the computational and communication challenges in federated contextual linear bandits. FSCLB utilizes Singular Value Decomposition (SVD) and a double-sketch strategy to significantly reduce the complexity of determinant calculations and parameter uploads. This approach cuts down computational costs from O(d^3) to O(l^2d) and communication costs from O(d^2) to O(ld), where 'd' is the data dimension and 'l' is the sketch size. Experiments demonstrate that FSCLB achieves over 90% reduction in costs with only a minor impact on cumulative reward. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Reduces computational and communication overhead in federated learning, potentially enabling wider adoption of bandit algorithms on resource-constrained devices.

RANK_REASON Academic paper proposing a new algorithm for federated learning.

Read on arXiv cs.LG →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 · Hantao Yang, Hong Xie, Xutong Liu, Defu Lian ·

    Scaling Federated Linear Contextual Bandits via Sketching

    arXiv:2605.00500v1 Announce Type: new Abstract: In federated contextual linear bandits, high data dimensionality incurs prohibitive computation and communication costs: local agents perform $O(d^3)$-time determinant computation and upload $O(d^2)$ parameters, making existing algo…

  2. arXiv cs.LG TIER_1 · Defu Lian ·

    Scaling Federated Linear Contextual Bandits via Sketching

    In federated contextual linear bandits, high data dimensionality incurs prohibitive computation and communication costs: local agents perform $O(d^3)$-time determinant computation and upload $O(d^2)$ parameters, making existing algorithms unscalable, where $d$ is the dimension of…