mlsanityData to 7 Oct 2026

ES-MAML: Simple Hessian-Free Meta Learning

arXiv 1910.01215 ↗First posted 25 Sep 2019cs.LG cs.AI cs.NEcited by 57

Not on the map. Why?

Abstract (arXiv)

We introduce ES-MAML, a new framework for solving the model agnostic meta learning (MAML) problem based on Evolution Strategies (ES). Existing algorithms for MAML are based on policy gradients, and incur significant difficulties when attempting to estimate second derivatives using backpropagation on stochastic policies. We show how ES can be applied to MAML to obtain an algorithm which avoids the problem of estimating second derivatives, and is also conceptually simple and easy to implement. Moreover, ES-MAML can handle new types of nonsmooth adaptation operators, and other techniques for improving performance and estimation of ES methods become applicable. We show empirically that ES-MAML is competitive with existing methods and often yields better adaptation with fewer queries.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 10; 2023: 13; 2024: 7; 2025: 5; 2026: 1.

57 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  3. 2021A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inversecited by 53
  4. 2021On the Convergence Theory for Hessian-Free Bilevel Algorithmscited by 33
  5. 2021On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learningcited by 29
  6. 2023Evolutionary Reinforcement Learning: A Surveycited by 24
  7. 2021Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Surveycited by 23
  8. 2022Local Stochastic Bilevel Optimization with Momentum-Based Variance Reductioncited by 20
  9. 2021ZARTS: On Zero-order Optimization for Neural Architecture Searchcited by 17
  10. 2022TorchOpt: An Efficient Library for Differentiable Optimizationcited by 17
  11. 2023Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oraclescited by 16
  12. 2021Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGDcited by 14
38 more
  1. 2021Compositional federated learning: Applications in distributionally robust averaging and meta learningcited by 12
  2. 2024A CMDP-within-online framework for Meta-Safe Reinforcement Learningcited by 12
  3. 2021Large-Scale Meta-Learning with Continual Trajectory Shiftingcited by 9
  4. 2021MAML is a Noisy Contrastive Learner in Classificationcited by 9
  5. 2021Learning an Explicit Hyperparameter Prediction Function Conditioned on Taskscited by 9
  6. 2022Learning Symbolic Model-Agnostic Loss Functions via Meta-Learningcited by 9
  7. 2023Meta-learning in healthcare: A surveycited by 9
  8. 2021Few-shot Quality-Diversity Optimizationcited by 8
  9. 2023A First Order Meta Stackelberg Method for Robust Federated Learningcited by 7
  10. 2021Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learningcited by 6
  11. 2022Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networkscited by 6
  12. 2024Fully Zeroth-Order Bilevel Programming via Gaussian Smoothingcited by 6
  13. 2021Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learningcited by 5
  14. 2021Meta-Learning with Adjoint Methodscited by 5
  15. 2025Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learningcited by 5
  16. 2021Learning to acquire novel cognitive tasks with evolution, plasticity and meta-meta-learningcited by 4
  17. 2023Discovering Adaptable Symbolic Algorithms from Scratchcited by 4
  18. 2024A New First-Order Meta-Learning Algorithm with Convergence Guaranteescited by 4
  19. 2021Debiasing a First-order Heuristic for Approximate Bi-level Optimizationcited by 3
  20. 2024Role Play: Learning Adaptive Role-Specific Strategies in Multi-Agent Interactionscited by 3
  21. 2025Stochastic Bilevel Optimization with Heavy-Tailed Noisecited by 3
  22. 2021Neural Auto-Curriculacited by 2
  23. 2022Lazy Queries Can Reduce Variance in Zeroth-order Optimizationcited by 2
  24. 2022Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equationscited by 2
  25. 2023Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworkscited by 2
  26. 2023Dual Meta-Learning with Longitudinally Generalized Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespancited by 2
  27. 2023Achieving O(ε-1.5) Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimizationcited by 2
  28. 2025qNBO: quasi-Newton Meets Bilevel Optimizationcited by 2
  29. 2021Quality Evolvability ES: Evolving Individuals With a Distribution of Well Performing and Diverse Offspringcited by 1
  30. 2022A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalizationcited by 1
  31. 2023Differentiable Arbitrating in Zero-sum Markov Gamescited by 1
  32. 2023Meta Generative Flow Networks with Personalization for Task-Specific Adaptationcited by 1
  33. 2024Configurable Mirror Descent: Towards a Unification of Decision Makingcited by 1
  34. 2024Meta-Learning Neural Procedural Biasescited by 1
  35. 2024Black Box Meta-Learning Intrinsic Rewardscited by 1
  36. 2021ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spacescited by 0
  37. 2022Distributed Evolution Strategies Using TPUs for Meta-Learningcited by 0
  38. 2021Dynamic Channel Access via Meta-Reinforcement Learningcited by 0

50 most cited of 57 All 57 (JSON)