Scaling Federated Linear Contextual Bandits via Sketching

• URL: http://arxiv.org/abs/2605.00500v1
• Date: Fri, 01 May 2026 08:22:06 GMT
• Title: Scaling Federated Linear Contextual Bandits via Sketching
• Abstract summary: This paper proposes Federated Sketch Contextual Linear Bandits (FSCLB)<n>Experiments on both synthetic and real-world datasets show that FSCLB significantly reduces computational and communication costs by over 90 %.
• Score: 49.12000877146222
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 algorithms unscalable, where $d$ is the dimension of data. To relieve these scaling bottlenecks, this paper proposes Federated Sketch Contextual Linear Bandits (FSCLB). On the computation side, FSCLB uses SVD to indirectly obtain the determinant required for communication, eliminating the prohibitive cost of direct determinant calculation and cutting complexity from $O(d^3)$ to $O(l^2d)$ per round, where $l< d$ is the sketch size. On the communication side, FSCLB introduces a double-sketch strategy that reduces both upload and download costs from $O(d^2)$ to $O(ld)$. Naively involving sketch update into federated contextual linear bandits can destroy the local increment and invalidate the asynchronous communication condition; FSCLB solves this by replacing the covariance matrix with the sketch matrix when deciding whether to communicate. Theoretically, FSCLB achieves a regret bound of $\widetilde{O} ((\sqrt{d}+\sqrt{M\varepsilon_l})\sqrt{lT})$, where $\varepsilon_l$ is the upper bounded by the spectral tail of the covariance matrix; when $l$ exceeds the rank of the covariance matrix, the bound simplifies to $\widetilde{O}(\sqrt{ldT})$, matching the optimal no-sketch regret. Experiments on both synthetic and real-world datasets show that FSCLB significantly reduces computational and communication costs by over 90 \% while sacrificing only a negligible amount of cumulative reward.

Related papers

• Efficient Multinomial Logistic Bandit via Frequent Directions [36.600560776380874]
  A representative UCB-type algorithm, OFUL-MLogB, achieves a regret bound of $tildemathcalO(KdsqrtT)$, but still requires $mathcalO(K3d3)$ time and $mathcalO(K2d2)$ space per round.<n>We propose EOFD-MLogB, which integrates frequent directions matrix sketching into OFUL-MLogB.
  arXiv  Detail & Related papers  (2026-06-10T11:47:27Z)
• Mild Over-Parameterization Benefits Asymmetric Tensor PCA [12.923414933046574]
  Asymmetric PCA (ATPCA) is prototypical model for studying the trade-offs between sample complexity, computation, and memory.<n>We focus on the setting where $overlinek geq 4$ is even and consider descent-based algorithms under a limited memory budget.
  arXiv  Detail & Related papers  (2026-04-11T13:34:48Z)
• One Good Source is All You Need: Near-Optimal Regret for Bandits under Heterogeneous Noise [49.12618706309658]
  Source-Optimistic Adaptive Regret minimization (SOAR) is a novel algorithm that prunes high-variance sources using sharp variance-concentration bounds.<n>We show it achieves the optimal instance-dependent regret of standard single-source MAB with variance $*2$.<n>Our theoretical bounds represent a significant improvement over some proposed baselines.
  arXiv  Detail & Related papers  (2026-02-16T05:25:06Z)
• Trust Region Masking for Long-Horizon LLM Reinforcement Learning [20.589897184824878]
  Policy gradient methods for large language models optimize a surrogate objective computed from samples of a rollout policy.<n>When $_textroll ne _$, there is approximation error between the surrogate and the true objective.<n>We propose Trust Region Masking (TRM), which excludes entire sequences from gradient computation if any token violates the trust region.
  arXiv  Detail & Related papers  (2025-12-28T20:41:59Z)
• Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques [1.14219428942199]
  Large language models have transformed natural language processing, yet supervised fine-tuning (SFT) remains computationally intensive.<n>This paper formally proves that capabilities acquired through SFT can be approximated by a base transformer model.<n>We extend these results to practical scenarios with finite context lengths and partial dataset access.
  arXiv  Detail & Related papers  (2025-06-09T08:37:19Z)
• Federated Linear Bandits with Finite Adversarial Actions [20.1041278044797]
  We study a federated linear bandits model, where $M$ clients communicate with a central server to solve a linear contextual bandits problem. To address the unique challenges of adversarial finite action sets, we propose the FedSupLinUCB algorithm. We prove that FedSupLinUCB achieves a total regret of $tildeO(sqrtd T)$, where $T$ is the total number of arm pulls from all clients, and $d$ is the ambient dimension of the linear model.
  arXiv  Detail & Related papers  (2023-11-02T03:41:58Z)
• Corruption-Robust Offline Reinforcement Learning with General Function Approximation [60.91257031278004]
  We investigate the problem of corruption in offline reinforcement learning (RL) with general function approximation. Our goal is to find a policy that is robust to such corruption and minimizes the suboptimality gap with respect to the optimal policy for the uncorrupted Markov decision processes (MDPs)
  arXiv  Detail & Related papers  (2023-10-23T04:07:26Z)
• DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization [0.0]
  DADAO is the first decentralized, accelerated, asynchronous, primal, first-order algorithm to minimize a sum of $L$-smooth and $mu$-strongly convex functions distributed over a given network of size $n$. We show that our algorithm requires $mathcalO(nsqrtchisqrtfracLmulog(frac1epsilon)$ local and only $mathcalO(nsqrtchisqrtfracLmulog(
  arXiv  Detail & Related papers  (2022-07-26T08:47:54Z)
• Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs [111.75736569611159]
  We propose the first computationally efficient horizon-free algorithm for linear mixture MDPs. Our algorithm adapts a weighted least square estimator for the unknown transitional dynamic. This also improves upon the best-known algorithms in this setting when $sigma_k2$'s are known.
  arXiv  Detail & Related papers  (2022-05-23T17:59:18Z)
• Variance-Aware Confidence Set: Variance-Dependent Bound for Linear Bandits and Horizon-Free Bound for Linear Mixture MDP [76.94328400919836]
  We show how to construct variance-aware confidence sets for linear bandits and linear mixture Decision Process (MDP) For linear bandits, we obtain an $widetildeO(mathrmpoly(d)sqrt1 + sum_i=1Ksigma_i2) regret bound, where $d is the feature dimension. For linear mixture MDP, we obtain an $widetildeO(mathrmpoly(d)sqrtK)$ regret bound, where
  arXiv  Detail & Related papers  (2021-01-29T18:57:52Z)
• List-Decodable Mean Estimation in Nearly-PCA Time [50.79691056481693]
  We study the fundamental task of list-decodable mean estimation in high dimensions. Our algorithm runs in time $widetildeO(ndk)$ for all $k = O(sqrtd) cup Omega(d)$, where $n$ is the size of the dataset. A variant of our algorithm has runtime $widetildeO(ndk)$ for all $k$, at the expense of an $O(sqrtlog k)$ factor in the recovery guarantee
  arXiv  Detail & Related papers  (2020-11-19T17:21:37Z)
• Deep Learning Meets Projective Clustering [66.726500395069]
  A common approach for compressing NLP networks is to encode the embedding layer as a matrix $AinmathbbRntimes d$. Inspired by emphprojective clustering from computational geometry, we suggest replacing this subspace by a set of $k$ subspaces.
  arXiv  Detail & Related papers  (2020-10-08T22:47:48Z)
• Robust Interference Management for SISO Systems with Multiple Over-the-Air Computations [16.52374405363812]
  We consider the over-the-air computation of sums over a shared complex-valued MAC. Finding appropriate Tx-Rx scaling factors balance between a low error in the computation of $s_n$ and the interference induced by it.
  arXiv  Detail & Related papers  (2020-04-21T11:15:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.