On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “Collaborative Linear Bandits”

Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Boundscs.LG

New algorithms balance collaboration and adversarial behavior in linear bandits.

problem Minimizing regret in a collaborative linear bandit problem with adversarial agents.

method Robust collaborative phased elimination algorithm with tight analyses.

result Achieves near-optimal regret bounds of $O\left(α+ 1/\sqrt{M} ight) \sqrt{dT}$ for good agents.

Collaborative Linear Bandits Adversarial Agents Regret Minimization Robust Confidence Intervals Information Theory

2022-06-06abs ↗pdf ↗

Adaptive Sample Sharing for Multi Agent Linear Banditscs.LG

New algorithm reduces multi-agent bandit regret by sharing data.

problem Designing efficient collaboration between multi-agent linear bandits.

method Bandit Adaptive Sample Sharing (BASS) algorithm, without assumptions on bandit parameters structure.

result Validated through theoretical analysis and empirical evaluations, BASS outperforms current state-of-the-art.

multi-agent linear bandits regret minimization data sharing cluster structure

2023-09-15abs ↗pdf ↗

Federated Linear Contextual Banditsstat.ML

A collaborative algorithm reduces regret in federated linear contextual bandits.

problem Optimizing decision-making in federated learning with heterogeneous data.

method Fed-PE algorithm, leveraging geometric structure of rewards, multi-client G-optimal design.

result Achieves near-optimal regrets with logarithmic communication costs.

federated learning contextual bandits heterogeneity collinearly-dependent policies near-optimal regrets

2021-10-27abs ↗pdf ↗

Federated Online Sparse Decision Makingstat.ML

A new algorithm reduces communication costs for collaborative decision-making across clients.

problem Collaborative decision-making with sparse rewards and heterogeneous contexts.

method Federated Lasso algorithm for sparse linear contextual bandits.

result Achieves near-optimal regret with logarithmic communication costs.

Federated Learning Sparse Bandits Collaborative Decision Making Regret Minimization

2022-02-27abs ↗pdf ↗

Federated Online and Bandit Convex Optimizationcs.LG

Study on collaborative vs. non-collaborative online and bandit convex optimization.

problem Minimizing average regret in distributed online and bandit convex optimization.

method Analyzes the impact of collaboration in adaptive and zeroth-order feedback settings.

result Collaboration is beneficial in high-dimensional federated online optimization with limited feedback.

federated learning online optimization bandit convex optimization adaptive adversary

2023-11-29abs ↗pdf ↗

Multi-Agent Low-Dimensional Linear Banditscs.LG

Agents collaborate to reduce regret in a multi-agent linear bandit problem with side information.

problem Reducing regret in a multi-agent stochastic linear bandit with side information.

method A decentralized algorithm where agents communicate subspace indices and each plays a projected LinUCB on the corresponding low-dimensional subspace.

result Per-agent finite-time regret is much smaller when agents communicate compared to non-communicating case.

multi-agent linear bandits side information subspaces regret minimization

2020-07-02abs ↗pdf ↗

Collaborative Multi-Agent Heterogeneous Multi-Armed Banditscs.LG

Study collaborative learning among multi-agents in multi-armed bandits.

problem Minimizing group cumulative regret in a heterogeneous multi-agent setting.

method Developed decentralized algorithms for collaboration between

N

agents learning

M

stochastic multi-armed bandits.

result Proved near-optimal behavior of proposed algorithms for group regret.

multi-agent systems heterogeneous multi-armed bandits collaborative learning regret minimization

2023-05-30abs ↗pdf ↗

Alternating Linear Bandits for Online Matrix-Factorization Recommendationcs.IR

We consider the problem of online collaborative filtering in the online setting, where items are recommended to the users over time. At each time step, the user (selected by the environment) consumes an item (selected by the agent) and provides a rating of the selected item. In this paper, we propose a novel algorithm …

2018-10-22abs ↗pdf ↗

Collaborative Filtering Banditscs.LG

Classical collaborative filtering, and content-based filtering methods try to learn a static recommendation model given training data. These approaches are far from ideal in highly dynamic recommendation domains such as news recommendation and computational advertisement, where the set of items and users is very fluid.…

2015-02-11abs ↗pdf ↗

Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraintscs.IR

Algorithm maximizes user rewards under per-item budget constraints.

problem Maximizing cumulative rewards in collaborative bandits with budget constraints.

method Collaborative algorithm B-LATTICE that clusters users and collaborates across groups.

result Achieves sub-linear regret bounds matching minimax bounds.

Collaborative Bandits Budget Constraints Latent Clustering Matrix Completion Regret Minimization

2023-10-31abs ↗pdf ↗

Optimal Regret Bounds for Collaborative Learning in Banditscs.LG

Optimal algorithm found for collaborative learning in bandits with optimal regret bounds.

problem Minimizing regret in collaborative multi-agent bandit problems.

method Proposed an algorithm with optimal regret bounds for collaborative multi-agent multi-armed bandit model.

result First algorithm with order optimal regret bounds for collaborative bandit model.

collaborative learning bandits regret minimization multi-agent multi-armed

2023-12-15abs ↗pdf ↗

Residual Bootstrap Exploration for Stochastic Linear Banditstat.ML

A new algorithm improves stochastic linear bandit performance using residual bootstrap.

problem Improving performance in stochastic linear bandit problems.

method Residual bootstrap exploration to estimate mean reward and pull the arm with the highest estimate.

result Proposed algorithm exttt{LinReBoot} achieves high-probability sub-linear regret under mild conditions.

stochastic linear bandit residual bootstrap online learning sub-linear regret optimism

2022-02-23abs ↗pdf ↗

Collaborative Learning in Kernel-based Bandits for Distributed Usersstat.ML

Algorithm optimizes collaborative learning among distributed clients using kernel-based bandits.

problem Optimizing personalized objectives in a distributed system with limited global information.

method Kernel-based bandit framework with surrogate Gaussian process models, sparse approximations.

result Order-optimal regret performance (up to polylogarithmic factors) and reduced communication overhead.

Collaborative Learning Kernel-based Bandits Distributed Systems Gaussian Processes Regret Analysis

2022-07-16abs ↗pdf ↗

Collaborative Min-Max Regret in Grouped Multi-Armed Banditscs.LG

New algorithm balances exploration cost between groups in multi-armed bandits.

problem Balancing exploration cost between groups in multi-armed bandits.

method Introducing Col-UCB algorithm that dynamically coordinates exploration across groups.

result Achieves optimal minimax and instance-dependent collaborative regret up to logarithmic factors.

multi-armed bandits grouped setting collaborative regret UCB algorithm exploration cost

2025-06-12abs ↗pdf ↗

Byzantine-Robust Federated Linear Banditscs.LG

Paper addresses robust federated linear bandits against Byzantine attacks.

problem Byzantine attacks on a small fraction of agents in federated learning.

method Proposes a geometric median-based robust aggregation oracle.

result Achieves sublinear regret bound of

ilde{\mathcal{O}}({T^{3/4}})

robust to fewer than half Byzantine agents.

federated learning linear bandits Byzantine attacks robust aggregation geometric median

2022-04-03abs ↗pdf ↗

On Regret-optimal Cooperative Nonstochastic Multi-armed Banditsstat.ML

New algorithm reduces regret in collaborative multi-agent bandit problems.

problem Optimizing decisions in a network of agents with communication delays.

method Follow-the-Regularized-Leader (FTRL) algorithm with suitable regularizers and communication protocols.

result Upper bound on individual regret matches lower bound up to a constant factor.

multi-agent bandits regret minimization collaborative decision-making communication delays

2022-11-30abs ↗pdf ↗

Partner-Aware Algorithms in Decentralized Cooperative Bandit Teamscs.LG

Partner-aware algorithms improve AI collaboration in multi-agent settings.

problem Improving AI cooperation in teams with shared rewards.

method Proposed Partner-Aware strategy extending Upper Confidence Bound for decentralized MAB.

result Achieves logarithmic regret in collaborative decision-making.

Decentralized MAB Upper Confidence Bound Logarithmic Regret Human-AI Collaboration

2021-10-02abs ↗pdf ↗

Near-Optimal Collaborative Learning in Banditscs.LG

New algorithm for collaborative bandit learning reduces sample complexity and regret.

problem Optimal arm identification in a multi-agent bandit model with communication.

method Phased elimination with data-dependent sampling schemes.

result Near-optimal algorithm for pure exploration in collaborative bandit learning.

Collaborative Learning Bandit Algorithms Mixed Rewards Regret Minimization Federated Learning

2022-05-31abs ↗pdf ↗

Cooperative Multi-Agent Constrained Stochastic Linear Banditscs.LG

Agents collaborate to minimize regret while keeping costs under a threshold.

problem Collaborative multi-agent stochastic linear bandits with cost constraints.

method Safe distributed upper confidence bound algorithm (MA-OPLB) with accelerated consensus.

result Regret bound of order $ \mathcal{O}\left(\frac{d}{τ-c_0}\frac{\log(NT)^2}{\sqrt{N}}\sqrt{\frac{T}{\log(1/|λ_2|)}} ight)$.

multi-agent systems stochastic bandits regret minimization distributed algorithms consensus

2024-10-22abs ↗pdf ↗

Multi-Player Approaches for Dueling Banditscs.LG

New algorithms improve dueling bandit performance in multiplayer settings.

problem Challenges in collaborative exploration of non-informative arm pairs in multiplayer dueling bandits.

method Demonstrated Follow Your Leader approach and message-passing fully distributed protocol.

result Multiplayer algorithms outperform single-player benchmarks.

dueling bandits multiplayer exploration collaborative Follow Your Leader

2024-05-25abs ↗pdf ↗

FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clientscs.LG

FedConPE improves conversational recommender systems efficiency and privacy.

problem Efficiently eliciting user preferences in interactive systems with heterogeneous clients.

method Phase elimination-based federated conversational bandit algorithm with adaptive key term construction.

result Minimizes uncertainty across all dimensions in feature space and offers improved efficiency and privacy.

Federated Learning Conversational Bandits Heterogeneous Clients Minimax Near-Optimal Cumulative Regret

2024-05-05abs ↗pdf ↗

Robust Multi-Agent Multi-Armed Banditscs.LG

New algorithm reduces regret in multi-agent bandits with malicious agents.

problem Collaboration between honest and malicious agents in multi-armed bandits.

method Dynamic reduction of communication with malicious agents, learning who is malicious.

result Algorithm reduces regret even with a single malicious agent, assuming

m

is small compared to

K

multi-agent multi-armed bandits malicious agents regret reduction dynamic communication

2020-07-07abs ↗pdf ↗

Distributed Bandit Learning: Near-Optimal Regret with Efficient Communicationcs.LG

We study the problem of regret minimization for distributed bandits learning, in which $M$ agents work collaboratively to minimize their total regret under the coordination of a central server. Our goal is to design communication protocols with near-optimal regret and little communication cost, which is measured by the…

2019-04-12abs ↗pdf ↗

On Context-Dependent Clustering of Banditscs.LG

We investigate a novel cluster-of-bandit algorithm CAB for collaborative recommendation tasks that implements the underlying feedback sharing mechanism by estimating the neighborhood of users in a context-dependent manner. CAB makes sharp departures from the state of the art by incorporating collaborative effects into …

2016-08-06abs ↗pdf ↗

Collaborative Learning with Limited Interaction: Tight Bounds for Distributed Exploration in Multi-Armed Banditscs.LG

Best arm identification (or, pure exploration) in multi-armed bandits is a fundamental problem in machine learning. In this paper we study the distributed version of this problem where we have multiple agents, and they want to learn the best arm collaboratively. We want to quantify the power of collaboration under limi…

2019-04-05abs ↗pdf ↗

Doubly Adversarial Federated Banditsstat.ML

A new federated bandit problem with multiple adversaries, solved with a near-optimal algorithm.

problem Non-stochastic federated multi-armed bandit problem with multiple adversaries.

method Proposed a near-optimal federated bandit algorithm called FEDEXP3.

result Guaranteed sub-linear regret without exchanging sequences of selected arm identities or loss sequences among agents.

federated learning multi-armed bandits adversarial regret minimization federated bandit algorithm

2023-01-22abs ↗pdf ↗

On Collaboration in Distributed Parameter Estimation with Resource Constraintscs.LG

Optimizes resource allocation for distributed parameter estimation in sensor networks.

problem Maximizing accuracy in parameter estimation with limited resources.

method Formulates a data collection and collaboration policy design problem as a Fisher information maximization problem. Proposes multi-armed bandit algorithms for learning the optimal policy.

result Identifies optimal data collection and collaboration policies that balance resource use and estimation accuracy.

distributed parameter estimation resource allocation sensor networks Fisher information Cramer-Rao bound

2023-07-12abs ↗pdf ↗

Federated Learning for Heterogeneous Bandits with Unobserved Contextscs.LG

A federated learning algorithm tackles unknown contexts in multi-arm bandits.

problem Learning optimal actions in federated multi-arm bandits with unobserved contexts.

method Elimination-based algorithm for linearly parametrized reward functions.

result Proved regret bound for linearly parametrized reward functions.

federated learning multi-arm bandits unknown contexts regret bound elimination-based algorithm

2023-03-29abs ↗pdf ↗

Optimum-statistical Collaboration Towards General and Efficient Black-box Optimizationstat.ML

Optimum-statistical collaboration improves black-box optimization efficiency.

problem Improving black-box optimization efficiency through better statistical collaboration.

method Introducing optimum-statistical collaboration framework for hierarchical bandits-based optimization.

result Demonstrated improved regret bounds and better performance in experiments.

black-box optimization hierarchical bandits optimum-statistical collaboration regret bounds variance-adaptive algorithm

2021-06-17abs ↗pdf ↗

OL4EL: Online Learning for Edge-cloud Collaborative Learning on Heterogeneous Edges with Resource Constraintscs.DC

OL4EL optimizes edge learning on resource-constrained servers.

problem Resource constraints on edge servers hinder effective distributed machine learning.

method Online Learning for EL (OL4EL) framework using budget-limited multi-armed bandit model.

result OL4EL significantly improves learning performance while conserving resources.

Edge Learning Resource Constraints Online Learning Bandit Algorithms Machine Learning

2020-04-22abs ↗pdf ↗

Context-Aware Banditscs.LG

We propose an efficient Context-Aware clustering of Bandits (CAB) algorithm, which can capture collaborative effects. CAB can be easily deployed in a real-world recommendation system, where multi-armed bandits have been shown to perform well in particular with respect to the cold-start problem. CAB utilizes a context-a…

2015-10-12abs ↗pdf ↗

Online Policy Learning and Inference by Matrix Completionstat.ML

New method learns decisions from collective preferences without individual covariates.

problem Making decisions online without individual covariates.

method Collaborative filtering, matrix completion bandit, ε-greedy policy, online gradient descent, inverse propensity weighting.

result Method outperforms benchmarks and reveals new discoveries.

policy learning matrix completion collaborative filtering online decision making covariate-free

2024-04-26abs ↗pdf ↗

Sequential Matrix Completioncs.IR

We propose a novel algorithm for sequential matrix completion in a recommender system setting, where the $(i,j)$ th entry of the matrix corresponds to a user $i$ 's rating of product $j$ . The objective of the algorithm is to provide a sequential policy for user-product pair recommendation which will yield the highest pos…

2017-10-23abs ↗pdf ↗

Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithmsstat.ML

Paper solves stochastic contextual linear bandits using linear bandit algorithms.

problem Stochastic contextual linear bandits with unknown context distribution.

method Establishes a reduction framework to convert to linear bandit problems.

result Achieves nearly optimal regret bound of

O(d\sqrt{T\log T})

stochastic contextual bandits linear bandit algorithms context distribution regret bound open problem

2022-11-08abs ↗pdf ↗

Federated X-Armed Banditstat.ML

A new federated algorithm reduces regret in X-armed bandit problems.

problem Collaborative optimization of heterogeneous local objectives.

method Fed-PNE algorithm using hierarchical partitioning and weak smoothness.

result Achieves sublinear cumulative regret with minimal communication.

federated learning X-armed bandit heterogeneous objectives sublinear regret privacy protection

2022-05-30abs ↗pdf ↗

Optimal Thresholding Linear Banditstat.ML

Optimal algorithm for identifying best arm in stochastic linear bandits with fixed confidence.

problem Identifying the best arm in stochastic linear bandits with fixed confidence.

method Extending an algorithm designed for Best Arm Identification to the

ε

-Thresholding Bandit Problem (TBP).

result Asymptotically optimal algorithm for TBP.

Thresholding Bandit Stochastic Linear Bandits Best Arm Identification Fixed Confidence

2024-02-11abs ↗pdf ↗

The Gossiping Insert-Eliminate Algorithm for Multi-Agent Banditscs.LG

We consider a decentralized multi-agent Multi Armed Bandit (MAB) setup consisting of $N$ agents, solving the same MAB instance to minimize individual cumulative regret. In our model, agents collaborate by exchanging messages through pairwise gossip style communications on an arbitrary connected graph. We develop two no…

2020-01-15abs ↗pdf ↗

A Parallel algorithm for

\mathcal{X}

-Armed banditsstat.ML

The target of $\mathcal{X}$ -armed bandit problem is to find the global maximum of an unknown stochastic function $f$ , given a finite budget of $n$ evaluations. Recently, $\mathcal{X}$ -armed bandits have been widely used in many situations. Many of these applications need to deal with large-scale data sets. To deal with…

2015-10-26abs ↗pdf ↗

Collaborative Learning of Stochastic Bandits over a Social Networkcs.LG

We consider a collaborative online learning paradigm, wherein a group of agents connected through a social network are engaged in playing a stochastic multi-armed bandit game. Each time an agent takes an action, the corresponding reward is instantaneously observed by the agent, as well as its neighbours in the social n…

2016-02-29abs ↗pdf ↗

Robust Multi-Agent Bandits Over Undirected Graphscs.LG

New algorithm reduces regret in multi-agent bandits over undirected graphs.

problem Minimize regret in a multi-agent bandit setting with malicious agents.

method Proposed a new algorithm for undirected graphs, considering the number of malicious neighbors.

result The new algorithm achieves nearly linear regret improvement over existing methods.

multi-agent bandits undirected graphs regret minimization malicious agents complete graph

2022-02-28abs ↗pdf ↗

Approximation Theory Based Methods for RKHS Banditscs.LG

New algorithms tackle RKHS bandits with reduced complexity and improved performance.

problem Adversarial and stochastic RKHS bandit problems with high computational complexity.

method Combining approximation theory with misspecified linear bandit methods.

result First general algorithm for adversarial RKHS bandit problem.

approximation theory RKHS bandits misspecified linear bandit stochastic bandits adversarial bandits

2020-10-23abs ↗pdf ↗

Locally Differentially Private (Contextual) Bandits Learningcs.LG

Paper tackles LDP bandits learning with improved results and sub-linear regret.

problem Contextual bandits learning with LDP privacy constraints.

method Simple black-box reduction frameworks for context-free bandits, extended to GLB.

result First result for BCO with multi-point feedback under LDP, sub-linear regret for GLB.

Locally Differential Privacy Bandits Learning Contextual Bandits Privacy Guarantees Sub-linear Regret

2020-06-01abs ↗pdf ↗

Nonlinear Data Integration via Kernel Methods for Data Collaboration Analysiscs.LG

NKI integrates obfuscated datasets using nonlinear kernels for improved data collaboration.

problem Privacy-preserving data collaboration with reduced reconstruction risk.

method Formulates linear kernel integration, kernelizes it, and introduces graph regularization and centering constraints.

result NKI improves classification accuracy over existing linear integration methods under nonlinear dimensionality reduction.

data collaboration kernel methods nonlinear integration privacy-preserving reconstruction risk

2026-05-26abs ↗pdf ↗

Personalized Collaborative Learning with Affinity-Based Variance Reductionstat.ML

PCL tackles collaborative learning for diverse agents, reducing sample complexity.

problem Balancing collaborative speedup with personalization for heterogeneous agents.

method AffPCL, with bias and importance correction mechanisms.

result AffPCL reduces sample complexity by a factor of

\max\{n^{-1}, δ\}

, where

n

is the number of agents and

δ\in[0,1]

measures heterogeneity.

multi-agent learning personalized learning heterogeneous agents bias correction importance correction

2025-10-17abs ↗pdf ↗

Robust Stochastic Linear Contextual Bandits Under Adversarial Attacksstat.ML

First robust bandit algorithm for contextual bandits with sub-linear regret.

problem Vulnerability of linear contextual bandit algorithms to adversarial attacks.

method Proposes a robust bandit algorithm for stochastic linear contextual bandits under fully adaptive and omniscient attacks.

result Sub-linear regret under various attacks without requiring attack information.

robust bandits contextual bandits adversarial attacks sub-linear regret recommender systems

2021-06-05abs ↗pdf ↗

Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Banditscs.LG

New algorithms improve linear bandit performance with low computation.

problem Optimizing reward in linear stochastic bandits.

method Reward-biased maximum likelihood method modified for linear and generalized linear bandits.

result New policies achieve order-optimality and competitive empirical performance.

bandits maximum likelihood linear stochastic optimization

2020-10-08abs ↗pdf ↗

Adversarial Combinatorial Bandits with General Non-linear Reward Functionsstat.ML

Study non-linear combinatorial bandits with polynomial rewards, finding significant differences from linear cases.

problem Adversarial combinatorial bandits with general non-linear reward functions.

method Extending existing work on adversarial linear combinatorial bandits, analyzing minimax optimal regret for polynomial and non-polynomial reward functions.

result Minimax optimal regret bounds for adversarial combinatorial bandits with general non-linear reward functions.

Adversarial Bandits Non-Linear Reward Polynomial Reward Regret Analysis Combinatorial Optimization

2021-01-05abs ↗pdf ↗

Personalized Federated X -armed Banditstat.ML

A new algorithm optimizes local objectives in federated learning with heterogeneous clients.

problem Optimizing local objectives in federated learning with heterogeneous client data.

method Proposes PF-PNE algorithm with double elimination strategy.

result PF-PNE algorithm optimizes local objectives with arbitrary heterogeneity and protects client data confidentiality.

federated learning heterogeneous clients bandit problem double elimination privacy protection

2023-10-25abs ↗pdf ↗