mlsanityData to 7 Oct 2026

Bandits on graphs and structures

arXiv 2605.03493 ↗First posted 5 May 2026cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

The goal of this thesis is to investigate the structural properties of certain sequential problems in order to bring the solutions closer to a practical use. In the first part, we put a special emphasis on structures that can be represented as graphs on actions. In the second part, we study the large action spaces that can be of exponential size in the number of base actions or even infinite. For graph bandits, we consider the settings of smoothness of rewards (spectral bandits), side observations, and influence maximization. For large structured domains, we cover kernel bandits, polymatroid bandits, bandits for function optimization (including unknown smoothness), and infinitely many-arms bandits. The thesis aspires to be a survey of the author's contributions on graph and structured bandits.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 41 of its 139 references that are in the map. First posted on arXiv 5 May 2026.

Builds on

41 of 139 references.

References · 41

  1. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  2. 2015Explore no more: Improved high-probability regret bounds for non-stochastic banditscited by 120
  3. 2014Online Clustering of Banditscited by 99
  4. 2015Less is More: Nystr"om Computational Regularizationcited by 89
  5. 2015Online Learning with Feedback Graphs: Beyond Banditscited by 79
  6. 2014Combinatorial Multi-Armed Bandit and Its Extension to Probabilistically Triggered Armscited by 78
  7. 2016Delay and Cooperation in Nonstochastic Banditscited by 71
  8. 2014Nonstochastic Multi-Armed Bandits with Graph-Structured Feedbackcited by 61
  9. 2016Distributed Clustering of Linear Bandits in Peer to Peer Networkscited by 50
  10. 2013A Gang of Banditscited by 49
  11. 2015Simple regret for infinitely many armed banditscited by 39
  12. 2014Unimodal Bandits: Regret Lower Bounds and Optimal Algorithmscited by 36
29 more
  1. 2014Matroid Bandits: Fast Combinatorial Optimization with Learningcited by 29
  2. 2016Collaborative Learning of Stochastic Bandits over a Social Networkcited by 29
  3. 2013From Bandits to Experts: A Tale of Domination and Independencecited by 28
  4. 2016Online Learning with Feedback Graphs Without the Graphscited by 27
  5. 2014Bandit Algorithms for Tree Searchcited by 25
  6. 2013An efficient algorithm for learning with semi-bandit feedbackcited by 21
  7. 2014Fast Randomized Kernel Methods With Statistical Guaranteescited by 21
  8. 2015Online Influence Maximization (Extended Version)cited by 17
  9. 2015Online Learning with Gaussian Payoffs and Side Observationscited by 15
  10. 2015Influence Maximization with Banditscited by 12
  11. 2014Online Stochastic Optimization under Correlated Bandit Feedbackcited by 11
  12. 2026Stochastic simultaneous optimistic optimizationcited by 7
  13. 2013Adaptive-treed banditscited by 6
  14. 2015Cheap Banditscited by 6
  15. 2016Multistage Campaigning in Social Networkscited by 5
  16. 2026Spectral Thompson samplingcited by 5
  17. 2026Blazing the trails before beating the path: Sample-efficient Monte-Carlo planningcited by 5
  18. 2026Efficient learning by implicit exploration in bandit problems with side observationscited by 5
  19. 2026Online learning with noisy side observationscited by 4
  20. 2016Online Influence Maximization in Non-Stationary Social Networkscited by 3
  21. 2014Learning to Act Greedily: Polymatroid Semi-Banditscited by 2
  22. 2015Information Gathering in Networks via Active Explorationcited by 2
  23. 2016Stochastic Process Bandits: Upper Confidence Bounds Algorithms via Generic Chainingcited by 2
  24. 2016Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedbackcited by 2
  25. 2026Analysis of Nystrom method with sequential ridge leverage scorescited by 2
  26. 2026Revealing graph bandits for maximizing local influencecited by 2
  27. 2026Black-box optimization of noisy functions with unknown smoothnesscited by 2
  28. 2016Adaptive Influence Maximization in Social Networks: Why Commit when You can Adapt?cited by 1
  29. 2026Online learning with ErdHos-R'enyi side-observation graphscited by 1

Built on by

Not cited yet.