mlsanityData to 14 Oct 2026

Meta-Curvature

arXiv 1902.03356 ↗First posted 9 Feb 2019cs.LG stat.MLcited by 70

Not on the map. Why?

Abstract (arXiv)

We propose meta-curvature (MC), a framework to learn curvature information for better generalization and fast model adaptation. MC expands on the model-agnostic meta-learner (MAML) by learning to transform the gradients in the inner optimization such that the transformed gradients achieve better generalization performance to a new task. For training large scale neural networks, we decompose the curvature matrix into smaller matrices in a novel scheme where we capture the dependencies of the model's parameters with a series of tensor products. We demonstrate the effects of our proposed method on several few-shot learning tasks and datasets. Without any task specific techniques and architectures, the proposed method achieves substantial improvement upon previous MAML variants and outperforms the recent state-of-the-art methods. Furthermore, we observe faster convergence rates of the meta-training process. Finally, we present an analysis that explains better generalization performance with the meta-trained curvature.

Key facts. Cited by 70 papers in the map (data through 14 Oct 2026). First posted on arXiv 9 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 23; 2023: 12; 2024: 7; 2025: 6; 2026: 4.

70 papers.

Sort:

By area:

  1. 2022Transformers learn in-context by gradient descentcited by 732
  2. 2021Fast Model Editing at Scalecited by 498
  3. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 187
  4. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  5. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 153
  6. 2021On Learning the Geodesic Path for Incremental Learningcited by 85
  7. 2021Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyondcited by 63
  8. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 58
  9. 2022Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Modelscited by 57
  10. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  11. 2023A Closer Look at Few-shot Classification Againcited by 46
  12. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
38 more
  1. 2021Bootstrapped Meta-Learningcited by 45
  2. 2023MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learningcited by 40
  3. 2021Learning where to learn: Gradient sparsity in meta and continual learningcited by 33
  4. 2022On Learning Fairness and Accuracy on Multiple Subgroupscited by 32
  5. 2021ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognitioncited by 29
  6. 2022MetaAudio: A Few-Shot Audio Classification Benchmarkcited by 24
  7. 2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
  8. 2022Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Predictioncited by 21
  9. 2022Channel Importance Matters in Few-Shot Image Classificationcited by 20
  10. 2022Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classificationcited by 16
  11. 2021On sensitivity of meta-learning to support datacited by 15
  12. 2022Transformer-Based Learned Optimizationcited by 13
  13. 2023Meta-Learning with a Geometry-Adaptive Preconditionercited by 11
  14. 2021MetaDelta: A Meta-Learning System for Few-shot Image Classificationcited by 10
  15. 2022Amortized Proximal Optimizationcited by 9
  16. 2022Few-Shot Learning by Dimensionality Reduction in Gradient Spacecited by 8
  17. 2021Stateless Neural Meta-Learning using Second-Order Gradientscited by 7
  18. 2022Meta Mirror Descent: Optimiser Learning for Fast Convergencecited by 7
  19. 2022On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptationcited by 7
  20. 2021A Channel Coding Benchmark for Meta-Learningcited by 6
  21. 2021Uniform Sampling over Episode Difficultycited by 6
  22. 2022Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptilecited by 6
  23. 2023A Meta-Learning Perspective on Transformers for Causal Language Modelingcited by 5
  24. 2025CAMEx: Curvature-aware Merging of Expertscited by 5
  25. 2022Fully Online Meta-Learning Without Task Boundariescited by 4
  26. 2022Meta-ticket: Finding optimal subnetworks for few-shot learning within randomly initialized neural networkscited by 4
  27. 2023Meta-Learning Adaptive Loss Functionscited by 4
  28. 2023Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detectioncited by 4
  29. 2023Meta Omnium: A Benchmark for General-Purpose Learning-to-Learncited by 4
  30. 2024Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learningcited by 4
  31. 2022Learning to Optimize Quasi-Newton Methodscited by 3
  32. 2023Are LSTMs Good Few-Shot Learners?cited by 3
  33. 2025Optimization-Inspired Few-Shot Adaptation for Large Language Modelscited by 3
  34. 2021Embedding Adaptation is Still Needed for Few-Shot Learningcited by 2
  35. 2021Online Hyperparameter Meta-Learning with Hypergradient Distillationcited by 2
  36. 2022Meta-free few-shot learning via representation learning with weight averagingcited by 2
  37. 2022Improving Meta-Learning Generalization with Activation-Based Early-Stoppingcited by 2
  38. 2022Unsupervised Few-shot Learning via Deep Laplacian Eigenmapscited by 2

50 most cited of 70 All 70 (JSON)