Research
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

84168251335 · Jun 202019922001200920172026
48 results for graph bandit

Investigates sequential problems on graph structures and large action spaces.

problem Sequential decision-making on graph structures and large action spaces.
method Spectral bandits, side observations, influence maximization, kernel bandits, polymatroid bandits, function optimization, infinitely many-arms bandits.
result Contributions to graph and structured bandits.

Graph-Triggered Bandits unify rested and restless bandits with graph-defined arm interactions.

problem Modeling sequential decision-making problems with evolving arm rewards.
method Graph-Triggered Bandits (GTBs) framework that generalizes rested and restless bandits using a graph.
result Rested and restless bandits are special cases of GTBs for suitable graphs.

New algorithms for causal bandits without knowing the graph structure.

problem Causal bandit problems with unknown graph structure.
method Developed novel causal bandit algorithms for causal trees, forests, and general graphs without prior knowledge of the causal graph.
result Regret guarantees significantly improved over standard MAB algorithms under mild conditions.

Graph neural Thompson Sampling improves online decision-making for graph data.

problem Online decision-making with graph-structured rewards.
method GNN-TS algorithm using GNN for mean reward estimation and graph neural tangent features for uncertainty.
result GNN-TS achieves a state-of-the-art regret bound of ildeO((ildedT)1/2) ilde{\mathcal{O}}(( ilde{d} T)^{1/2}).

Bandit is a framework for designing sequential experiments. In each experiment, a learner selects an arm AAA \in \mathcal{A} and obtains an observation corresponding to AA. Theoretically, the tight regret lower-bound for the general bandit is polynomial with respect to the number of arms A|\mathcal{A}|. This makes ba…

2018-06-06abs ↗pdf ↗

A UCB algorithm reduces regret in cooperative multi-agent graph bandits.

problem Cooperative multi-agent decision-making on a graph with shared rewards.
method Upper Confidence Bound (UCB) algorithm for minimizing regret.
result The Multi-G-UCB algorithm achieves expected regret O(γNlog(T)[KT+DK])O(γN\log(T)[\sqrt{KT} + DK]).

New algorithm reduces regret in graphical bilinear bandits.

problem Optimizing decisions in a network of agents playing bilinear games.
method Optimism in the face of uncertainty principle applied to combinatorial NP-hard problem.
result Upper bound of ildeO(T) ilde{O}(\sqrt{T}) on αα-regret demonstrated.

New approach combines semi-supervised learning and bandits for better predictions.

problem Online semi-supervised learning with bandit feedback for applications like clinical trials and ad recommendations.
method Adjusted Graph Convolutional Network (GCN) for contextual bandits, with semi-supervised missing rewards imputation.
result Developed multi-GCN embedded contextual bandit algorithms verified on real-world datasets.

Study bandit problem on smooth graph functions for recommender systems.

problem Online learning problems involving graphs, like content-based recommendation.
method Introduced spectral bandit problem and two algorithms that scale linearly in effective dimension.
result Learned user preferences for thousands of items from just tens nodes evaluations.

AGG-UCB uses neural networks to optimize group behaviors in contextual bandits.

problem Optimizing group behaviors in contextual bandits with mutual impacts.
method Introduces Arm Group Graph (AGG) and AGG-UCB algorithm using neural networks and graph neural networks.
result Achieves near-optimal regret bound with over-parameterized neural networks.

Bandit problem on graphs aims to recommend items with high expected ratings.

problem Online learning problems involving graphs, such as content-based recommendation.
method Study of a bandit problem on graphs, introducing effective dimension and proposing algorithms.
result Proposed algorithms scale linearly and sublinearly in the effective dimension, improving cumulative regret.

New graph feedback model for bandits with improved regret bounds.

problem Understanding how graph structure affects regret in bandit problems.
method Introduced fractional weak domination number and kk-packing independence number to capture upper and lower bounds on regret. Used strong duality theorem to derive upper and lower bounds.
result Proved general upper and lower bounds on regret for various graph structures, showing tightness up to a logarithmic factor.

The paper tackles a bandit problem on graphs with smooth functions, aiming to recommend items with high expected ratings.

problem Online learning problems involving graphs, such as content-based recommendation.
method Introduced the notion of effective dimension and proposed two algorithms for solving the problem.
result The algorithms can learn good estimators of user preferences from just tens of nodes evaluations.

This paper extends combinatorial semi-bandits to graph feedback, improving regret bounds.

problem Adversarial combinatorial semi-bandits with graph feedback.
method Introduced graph feedback in combinatorial semi-bandits, using convexified actions and online stochastic mirror descent.
result Optimal regret scales as ST+αSTS\sqrt{T}+\sqrt{αST}, interpolating between full and semi-bandit feedback.

New algorithm reduces regret in combinatorial causal bandits without graph structure.

problem Minimizing regret in combinatorial causal bandits without graph structure.
method Design of algorithms for binary general causal models and BGLMs without graph skeleton.
result Achieves O(TlnT)O(\sqrt{T}\ln T) expected regret for causal models and O(T23lnT)O(T^{\frac{2}{3}}\ln T) for BGLMs.

In this paper, we introduce a new online decision making paradigm that we call Thresholding Graph Bandits. The main goal is to efficiently identify a subset of arms in a multi-armed bandit problem whose means are above a specified threshold. While traditionally in such problems, the arms are assumed to be independent, …

2019-05-22abs ↗pdf ↗

New algorithm minimizes regret in multi-agent bandit problem with probabilistic communication.

problem Minimizing group regret in multi-agent multi-armed bandit problem with probabilistic communication.
method Proposes a new UCB-based algorithm for decentralized multi-agent multi-armed bandit problem on dd-regular graphs with probabilistic communication.
result The proposed algorithm outperforms state-of-the-art algorithms in minimizing group regret.

New algorithm learns causal graph to minimize regret in bandits without full structure.

problem Learning optimal decisions in bandits with unknown causal graph and latent confounders.
method Two-stage approach: first learns ancestors and necessary confounders, second applies standard bandit algorithm.
result No full causal structure needed for optimal decisions; only necessary confounders are crucial.

New algorithm reduces high-probability regret for time-varying feedback graphs.

problem High-probability regret bounds for adversarial bandits with time-varying feedback graphs.
method Online mirror descent framework with innovative techniques for pessimistic loss estimators.
result Achieves optimal high-probability regret bound for general and weakly observable graphs.

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.

A decentralized policy achieves logarithmic regret for multi-agent MAB problems with communication constraints.

problem Decentralized policy for multi-agent MAB problems with option availability and communication constraints.
method Upper Confidence Bound (UCB) algorithms with non-stationary stochastic communication protocol.
result Guaranteed logarithmic regret for non-fully connected spatial graphs with communication constraints.

Agents cooperate to make decisions in multi-armed bandits over a graph.

problem Optimizing decisions in multi-agent multi-armed bandits with shared information.
method Designs consensus-based distributed estimation and cooperative algorithms for group decision-making.
result Achieves group performance close to centralized fusion center.

We study multi-armed bandit problems with graph feedback, in which the decision maker is allowed to observe the neighboring actions of the chosen action, in a setting where the graph may vary over time and is never fully revealed to the decision maker. We show that when the feedback graphs are undirected, the original …

2018-05-23abs ↗pdf ↗

New algorithm tackles multi-agent bandits with heavy-tailed data.

problem Maximizing system performance in multi-agent settings with heavy-tailed data.
method Algorithm exploits hub-like structures and synchronization among clients.
result Regret bound of O(M11αlogT)O(M^{1 -\frac{1}α} \log{T}) for homogeneous settings, O(MlogT)O(M \log{T}) for heterogeneous.

We consider the partial observability model for multi-armed bandits, introduced by Mannor and Shamir. Our main result is a characterization of regret in the directed observability model in terms of the dominating and independence numbers of the observability graph. We also show that in the undirected case, the learner …

2013-07-17abs ↗pdf ↗

We study the stochastic multi-armed bandit problem with the graph-based feedback structure introduced by Mannor and Shamir. We analyze the performance of the two most prominent stochastic bandit algorithms, Thompson Sampling and Upper Confidence Bound (UCB), in the graph-based feedback setting. We show that these algor…

2019-05-23abs ↗pdf ↗

A novel algorithm minimizes regret in a multi-agent bandit problem with time-varying random graphs and heterogeneous rewards.

problem Minimizing regret in a multi-agent multi-armed bandit problem with time-varying random graphs and heterogeneous rewards.
method Introduces a novel algorithmic framework combining averaging-based consensus with a weighting technique and upper confidence bound.
result Derives optimal instance-dependent regret upper bounds of order logT\log{T} in both sub-gaussian and sub-exponential environments.

We study the adversarial multi-armed bandit problem where partial observations are available and where, in addition to the loss incurred for each action, a \emph{switching cost} is incurred for shifting to a new action. All previously known results incur a factor proportional to the independence number of the feedback …

2019-07-29abs ↗pdf ↗

Study on a new family of problems interpolating expert advice and multi-armed bandits.

problem A new family of problems combining expert advice and multi-armed bandits.
method Proved minimax regret bounds and designed optimal PAC algorithms for pure exploration.
result Tight minimax regret bounds and optimal PAC algorithm for m\mathbf{m}-BAI.

The paper tackles causal bandits for SEMs, proposing algorithms that avoid estimating 2N2^N reward distributions.

problem Designing an optimal sequence of interventions in causal graphical models to minimize cumulative regret.
method Proposes two algorithms for causal bandits for linear structural equation models (SEMs), avoiding the estimation of 2N2^N reward distributions.
result Cumulative regrets scale as ildeO(dL+12NT) ilde{\cal O} (d^{L+\frac{1}{2}} \sqrt{NT}) under bounded noise and parameter space.