mlsanityData to 7 Oct 2026

More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms

arXiv 2402.04054 ↗First posted 6 Feb 2024cs.LG stat.MLcited by 10

Not on the map. Why?

Abstract (arXiv)

We introduce a new framework for studying meta-learning methods using PAC-Bayesian theory. Its main advantage over previous work is that it allows for more flexibility in how the transfer of knowledge between tasks is realized. For previous approaches, this could only happen indirectly, by means of learning prior distributions over models. In contrast, the new generalization bounds that we prove express the process of meta-learning much more directly as learning the learning algorithm that should be used for future tasks. The flexibility of our framework makes it suitable to analyze a wide range of meta-learning mechanisms and even design new mechanisms. Other than our theoretical contributions we also show empirically that our framework improves the prediction quality in practical meta-learning mechanisms.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

23 of 40 references.

References · 23

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  3. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  4. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  5. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  6. 2021User-friendly introduction to PAC-Bayes boundscited by 234
  7. 2015The Benefit of Multitask Representation Learningcited by 194
  8. 2019A Primer on PAC-Bayesian Learningcited by 130
  9. 2020Tighter risk certificates for neural networkscited by 112
  10. 2020PACOH: Bayes-Optimal Meta-Learning with PAC-Guaranteescited by 85
  11. 2017Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theorycited by 76
  12. 2013A PAC-Bayesian bound for Lifelong Learningcited by 69
11 more
  1. 2023Generalization Bounds: Perspectives from Information Theory and PAC-Bayescited by 60
  2. 2019Learning-to-Learn Stochastic Gradient Descent with Biased Regularizationcited by 49
  3. 2021Generalization Bounds For Meta-Learning: An Information-Theoretic Analysiscited by 45
  4. 2021Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stabilitycited by 29
  5. 2021Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learningcited by 21
  6. 2023PeFLL: Personalized Federated Learning by Learning to Learncited by 21
  7. 2021PAC-Bayes Bounds for Meta-learning with Data-Dependent Priorcited by 11
  8. 2022Evaluated CMI Bounds for Meta Learning: Tightness and Expressivenesscited by 11
  9. 2022Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practicecited by 11
  10. 2023Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayescited by 8
  11. 2020PAC-Bayes meta-learning with implicit task-specific posteriorscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 2.

10 papers.

  1. 2025From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learningcited by 5
  2. 2024Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworkscited by 3
  3. 2025Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizescited by 2
  4. 2026Bound to Disagree: Generalization Bounds via Certifiable Surrogatescited by 2
  5. 2024Learning via Surrogate PAC-Bayescited by 1
  6. 2025Model Diffusion for Certifiable Few-shot Transfer Learningcited by 0
  7. 2025Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensionscited by 0
  8. 2025An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learningcited by 0
  9. 2025Representative Action Selection for Large Action Space: From Bandits to MDPscited by 0
  10. 2026A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learningcited by 0