mlsanityData to 7 Oct 2026

Online Meta-Learning

arXiv 1902.08438 ↗First posted 22 Feb 2019cs.LG cs.AI stat.MLcited by 137

Not on the map. Why?

Abstract (arXiv)

A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this problem as learning a prior over model parameters that is amenable for fast adaptation on a new task, but typically assumes the set of tasks are available together as a batch. In contrast, online (regret based) learning considers a sequential setting in which problems are revealed one after the other, but conventionally train only a single model without any task-specific adaptation. This work introduces an online meta-learning setting, which merges ideas from both the aforementioned paradigms to better capture the spirit and practice of continual lifelong learning. We propose the follow the meta leader algorithm which extends the MAML algorithm to this setting. Theoretically, this work provides an O(log T) regret guarantee with only one additional higher order smoothness assumption in comparison to the standard online setting. Our experimental evaluation on three different large-scale tasks suggest that the proposed algorithm significantly outperforms alternatives based on traditional online learning approaches.

Key facts. Cited by 137 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 27; 2023: 31; 2024: 28; 2025: 15; 2026: 12.

137 papers.

Sort:

By area:

  1. 2021An Empirical Investigation of the Role of Pre-training in Lifelong Learningcited by 134
  2. 2023A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learningcited by 66
  3. 2024From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examplescited by 55
  4. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  5. 2021Generalization Bounds For Meta-Learning: An Information-Theoretic Analysiscited by 45
  6. 2021How Fine-Tuning Allows for Effective Meta-Learningcited by 41
  7. 2023An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learningcited by 39
  8. 2021Towards mental time travel: a hierarchical memory for reinforcement learning agentscited by 38
  9. 2026MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wildcited by 35
  10. 2021On the Power of Multitask Representation Learning in Linear MDPcited by 30
  11. 2022Source-Free Progressive Graph Learning for Open-Set Domain Adaptationcited by 25
  12. 2024Task-driven Image Fusion with Learnable Fusion Losscited by 24
38 more
  1. 2022You Only Live Once: Single-Life Reinforcement Learningcited by 23
  2. 2022Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learningcited by 22
  3. 2023DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecastingcited by 21
  4. 2021Few-Shot Learning with Class Imbalancecited by 18
  5. 2021An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Datasetcited by 18
  6. 2022What Matters For Meta-Learning Vision Regression Tasks?cited by 18
  7. 2022Discrete Key-Value Bottleneckcited by 18
  8. 2022Adaptive Fairness-Aware Online Meta-Learning for Changing Environmentscited by 17
  9. 2023A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Taskscited by 17
  10. 2023Curious Replay for Model-based Adaptationcited by 16
  11. 2024SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Modelscited by 16
  12. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  13. 2022Landscape Learning for Neural Network Inversioncited by 15
  14. 2023MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognitioncited by 15
  15. 2023ReFusion: Learning Image Fusion from Reconstruction with Learnable Loss via Meta-Learningcited by 15
  16. 2022Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methodscited by 14
  17. 2022Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributionscited by 14
  18. 2024Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for Model-free LQRcited by 14
  19. 2021Conditional Meta-Learning of Linear Representationscited by 12
  20. 2021Compositional federated learning: Applications in distributionally robust averaging and meta learningcited by 12
  21. 2022Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead Adaptationcited by 12
  22. 2022Federated Learning and Meta Learning: Approaches, Applications, and Directionscited by 12
  23. 2023AUTO: Adaptive Outlier Optimization for Test-Time OOD Detectioncited by 12
  24. 2023When Meta-Learning Meets Online and Continual Learning: A Surveycited by 12
  25. 2024A CMDP-within-online framework for Meta-Safe Reinforcement Learningcited by 12
  26. 2021Towards a theory of out-of-distribution learningcited by 11
  27. 2023Towards Fair Disentangled Online Learning for Changing Environmentscited by 11
  28. 2024Gradient Methods with Online Scalingcited by 11
  29. 2023Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learningcited by 10
  30. 2023Meta-learning in healthcare: A surveycited by 9
  31. 2021Self-Attention Meta-Learner for Continual Learningcited by 8
  32. 2021Meta Learning on a Sequence of Imbalanced Domains with Difficulty Awarenesscited by 8
  33. 2021Spiking Generative Adversarial Networks With a Neural Network Discriminator: Local Training, Bayesian Models, and Continual Meta-Learningcited by 8
  34. 2023Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayescited by 8
  35. 2023Nonlinear Meta-Learning Can Guarantee Faster Ratescited by 8
  36. 2024Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policiescited by 8
  37. 2024Learning to Continually Learn with the Bayesian Principlecited by 8
  38. 2021Meta-Learning with Graph Neural Networks: Methods and Applicationscited by 7

50 most cited of 137 All 137 (JSON)