mlsanityData to 7 Oct 2026

Non-Stationary Representation Learning in Sequential Linear Bandits

arXiv 2201.04805 ↗First posted 13 Jan 2022cs.LG cs.SY eess.SYcited by 13

Not on the map. Why?

Abstract (arXiv)

In this paper, we study representation learning for multi-task decision-making in non-stationary environments. We consider the framework of sequential linear bandits, where the agent performs a series of tasks drawn from distinct sets associated with different environments. The embeddings of tasks in each set share a low-dimensional feature extractor called representation, and representations are different across sets. We propose an online algorithm that facilitates efficient decision-making by learning and transferring non-stationary representations in an adaptive fashion. We prove that our algorithm significantly outperforms the existing ones that treat tasks independently. We also conduct experiments using both synthetic and real data to validate our theoretical insights and demonstrate the efficacy of our algorithm.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 22 of its 47 references that are in the map. First posted on arXiv 13 Jan 2022.

Builds on

22 of 47 references.

References · 22

  1. 2020Few-Shot Learning via Learning the Representation, Provablycited by 213
  2. 2020On the Theory of Transfer Learning: The Importance of Task Diversitycited by 186
  3. 2020Provable Meta-Learning of Linear Representationscited by 161
  4. 2020Predicting What You Already Know Helps: Provable Self-Supervised Learningcited by 152
  5. 2019Provable Guarantees for Gradient-Based Meta-Learningcited by 67
  6. 2020Impact of Representation Learning in Linear Banditscited by 51
  7. 2015Massively Multitask Networks for Drug Discoverycited by 49
  8. 2017Multi-Task Learning for Contextual Banditscited by 47
  9. 2020Meta-learning with Stochastic Linear Banditscited by 45
  10. 2021Near-optimal Representation Learning for Linear Bandits and Linear RLcited by 45
  11. 2013Sequential Transfer in Multi-armed Bandit with Finite Set of Modelscited by 38
  12. 2020Distributed Cooperative Decision Making in Multi-agent Multi-armed Banditscited by 38
10 more
  1. 2021Online Multi-Armed Bandits with Adaptive Inferencecited by 21
  2. 2021Policy Learning with Adaptively Collected Datacited by 21
  3. 2019Tight Regret Bounds for Infinite-armed Linear Contextual Banditscited by 17
  4. 2019Learning in Restless Multi-Armed Bandits via Adaptive Arm Sequencing Rulescited by 15
  5. 2021One More Step Towards Reality: Cooperative Bandits with Imperfect Communicationcited by 15
  6. 2020A Dynamic Observation Strategy for Multi-agent Multi-armed Bandit Problemcited by 10
  7. 2015Satisficing in multi-armed bandit problemscited by 9
  8. 2018Multi-Player Bandits: A Trekking Approachcited by 9
  9. 2021When to Call Your Neighbor? Strategic Communication in Cooperative Stochastic Banditscited by 7
  10. 2021Nonstationary Stochastic Multiarmed Bandits: UCB Policies and Minimax Regretcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 4; 2024: 0; 2025: 2; 2026: 2.

13 papers.

Sort:

By area:

  1. 2023Transformers as Algorithms: Generalization and Stability in In-context Learningcited by 220
  2. 2022Provable Benefit of Multitask Representation Learning in Reinforcement Learningcited by 29
  3. 2022Nearly Minimax Algorithms for Linear Bandits with Shared Representationcited by 16
  4. 2022Provable and Efficient Continual Representation Learningcited by 14
  5. 2023Multi-task Representation Learning for Pure Exploration in Linear Banditscited by 6
  6. 2022Stochastic Multi-armed Bandits with Non-stationary Rewards Generated by a Linear Dynamical Systemcited by 3
  7. 2023Provable Pathways: Learning Multiple Tasks over Multiple Pathscited by 3
  8. 2022Representation Learning for Context-Dependent Decision-Makingcited by 1
  9. 2023Stochastic Contextual Bandits with Long Horizon Rewardscited by 1
  10. 2025Beyond Task Diversity: Provable Representation Transfer for Sequential Multi-Task Linear Banditscited by 1
  11. 2025Bridging Lifelong and Multi-Task Representation Learning via Algorithm and Complexity Measurecited by 0
  12. 2026Invariance-Based Dynamic Regret Minimizationcited by 0
1 more
  1. 2026RepUCB: Representation Learning-Based UCB for Heterogeneous Multi-Task Linear Banditscited by 0