mlsanityData to 7 Oct 2026

Recasting Gradient-Based Meta-Learning as Hierarchical Bayes

arXiv 1801.08930 ↗First posted 26 Jan 2018cs.LGcited by 180

Not on the map. Why?

Abstract (arXiv)

Meta-learning allows an intelligent agent to leverage prior learning episodes as a basis for quickly improving performance on a novel task. Bayesian hierarchical modeling provides a theoretical framework for formalizing meta-learning as inference for a set of parameters that are shared across tasks. Here, we reformulate the model-agnostic meta-learning algorithm (MAML) of Finn et al. (2017) as a method for probabilistic inference in a hierarchical Bayesian model. In contrast to prior methods for meta-learning via hierarchical Bayes, MAML is naturally applicable to complex function approximators through its use of a scalable gradient descent procedure for posterior inference. Furthermore, the identification of MAML as hierarchical Bayes provides a way to understand the algorithm's operation as a meta-learning procedure, as well as an opportunity to make use of computational strategies for efficient inference. We use this opportunity to propose an improvement to the MAML algorithm that makes use of techniques from approximate inference and curvature estimation.

Key facts. Cited by 180 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 62; 2022: 40; 2023: 30; 2024: 19; 2025: 13; 2026: 15.

180 papers.

Sort:

By area:

  1. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 218
  2. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  3. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  4. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  5. 2024Building Machines that Learn and Think with Peoplecited by 73
  6. 2021Continual Learning via Local Module Compositioncited by 61
  7. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 57
  8. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  9. 2021Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptationcited by 50
  10. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  11. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  12. 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46
38 more
  1. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  2. 2021Bootstrapped Meta-Learningcited by 45
  3. 2021Generalization Bounds For Meta-Learning: An Information-Theoretic Analysiscited by 45
  4. 2021Uncertainty-guided Model Generalization to Unseen Domainscited by 41
  5. 2023Modeling rapid language learning by distilling Bayesian priors into artificial neural networkscited by 40
  6. 2021Meta-Learning Dynamics Forecasting Using Task Inferencecited by 37
  7. 2022Few-Shot Diffusion Modelscited by 37
  8. 2018Learning a Prior over Intent via Meta-Inverse Reinforcement Learningcited by 36
  9. 2021Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Taskscited by 36
  10. 2021Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agentscited by 35
  11. 2022FedPop: A Bayesian Approach for Personalised Federated Learningcited by 35
  12. 2022Learning Domain Invariant Prompt for Vision-Language Modelscited by 35
  13. 2022A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biasescited by 30
  14. 2022Gradient Descent on Neurons and its Link to Approximate Second-Order Optimizationcited by 29
  15. 2021From partners to populations: A hierarchical Bayesian account of coordination and conventioncited by 27
  16. 2021Meta-Learning to Improve Pre-Trainingcited by 27
  17. 2023Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Modelscited by 26
  18. 2024Prompt Learning via Meta-Regularizationcited by 26
  19. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  20. 2022HyperShot: Few-Shot Learning by Kernel HyperNetworkscited by 24
  21. 2021The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learningcited by 23
  22. 2022The Neural Process Family: Survey, Applications and Perspectivescited by 23
  23. 2021Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platformscited by 22
  24. 2023Bayes in the age of intelligent machinescited by 22
  25. 2021Quantifying Visual Image Quality: A Bayesian Viewcited by 20
  26. 2023Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learningcited by 20
  27. 2021Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learningcited by 19
  28. 2021Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classificationcited by 18
  29. 2021Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approachcited by 18
  30. 2021An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Datasetcited by 18
  31. 2022Few-Shot Calibration of Set Predictors via Meta-Learned Cross-Validation-Based Conformal Predictioncited by 17
  32. 2021On Data Efficiency of Meta-learningcited by 16
  33. 2021Few-Shot Learning with a Strong Teachercited by 16
  34. 2022HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworkscited by 16
  35. 2023Meta Temporal Point Processescited by 16
  36. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  37. 2021One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Videocited by 14
  38. 2021A contrastive rule for meta-learningcited by 14

50 most cited of 180 All 180 (JSON)