mlsanityData to 7 Oct 2026

Meta-Learning via Learned Loss

arXiv 1906.05374 ↗First posted 12 Jun 2019cs.LG cs.AI cs.ROcited by 60

Not on the map. Why?

Abstract (arXiv)

Typically, loss functions, regularization mechanisms and other important aspects of training parametric models are chosen heuristically from a limited set of options. In this paper, we take the first step towards automating this process, with the view of producing models which train faster and more robustly. Concretely, we present a meta-learning method for learning parametric loss functions that can generalize across different tasks and model architectures. We develop a pipeline for meta-training such loss functions, targeted at maximizing the performance of the model trained under them. The loss landscape produced by our learned losses significantly improves upon the original task-specific losses in both supervised and reinforcement learning tasks. Furthermore, we show that our meta-learning framework is flexible enough to incorporate additional information at meta-train time. This information shapes the learned loss function such that the environment does not need to provide this information during meta-test time. We make our code available at https://sites.google.com/view/mlthree.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 15; 2022: 12; 2023: 11; 2024: 13; 2025: 5; 2026: 2.

60 papers.

Sort:

By area:

  1. 2022General-Purpose In-Context Learning by Meta-Learning Transformerscited by 102
  2. 2022Test-Time Adaptation via Conjugate Pseudo-labelscited by 98
  3. 2020Offline Meta-Reinforcement Learning with Advantage Weightingcited by 92
  4. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  5. 2023Hyperparameters in Reinforcement Learning and How To Tune Themcited by 58
  6. 2020Model-Based Inverse Reinforcement Learning from Visual Demonstrationscited by 52
  7. 2021Meta-learning PINN loss functionscited by 51
  8. 2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
  9. 2021Evolving Reinforcement Learning Algorithmscited by 48
  10. 2024Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Taskscited by 40
  11. 2022Compute-Efficient Deep Learning: Algorithmic Trends and Opportunitiescited by 38
  12. 2021MetaHTR: Towards Writer-Adaptive Handwritten Text Recognitioncited by 27
38 more
  1. 2024Prompt Learning via Meta-Regularizationcited by 26
  2. 2021Introducing Symmetries to Black Box Meta Reinforcement Learningcited by 25
  3. 2021Megaverse: Simulating Embodied Agents at One Million Experiences per Secondcited by 19
  4. 2021Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learningcited by 18
  5. 2024Discovering Temporally-Aware Reinforcement Learning Algorithmscited by 18
  6. 2023Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challengescited by 17
  7. 2023Discovering General Reinforcement Learning Algorithms with Adversarial Environment Designcited by 16
  8. 2023Neural Relational Inference with Fast Modular Meta-learningcited by 16
  9. 2023Behavior Alignment via Reward Function Optimizationcited by 16
  10. 2021CoMPS: Continual Meta Policy Searchcited by 15
  11. 2021Searching for Robustness: Loss Learning for Noisy Classification Taskscited by 13
  12. 2023Learning to Optimize for Reinforcement Learningcited by 12
  13. 2021A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learningcited by 11
  14. 2024Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timestepscited by 11
  15. 2022Learning Symbolic Model-Agnostic Loss Functions via Meta-Learningcited by 9
  16. 2023BC-IRL: Learning Generalizable Reward Functions from Demonstrationscited by 7
  17. 2021One Step at a Time: Pros and Cons of Multi-Step Meta-Gradient Reinforcement Learningcited by 5
  18. 2023Meta-Learning Adaptive Loss Functionscited by 4
  19. 2024Unlearning Personal Data from a Single Imagecited by 4
  20. 2022Open-Set Semi-Supervised Learning for 3D Point Cloud Understandingcited by 3
  21. 2023Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNscited by 3
  22. 2024AutoFT: Learning an Objective for Robust Fine-Tuningcited by 3
  23. 2025Kozax: Flexible and Scalable Genetic Programming in JAXcited by 3
  24. 2021Neural Auto-Curriculacited by 2
  25. 2023Writer adaptation for offline text recognition: An exploration of neural network-based methodscited by 2
  26. 2024Neural Loss Function Evolution for Large-Scale Image Classifier Convolutional Neural Networkscited by 2
  27. 2021Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learningcited by 1
  28. 2022Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stabilitycited by 1
  29. 2024Fast and Efficient Local Search for Genetic Programming Based Loss Function Learningcited by 1
  30. 2024Meta-Learning Neural Procedural Biasescited by 1
  31. 2024Black Box Meta-Learning Intrinsic Rewardscited by 1
  32. 2024EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classificationcited by 1
  33. 2025Bayesian Meta-Reinforcement Learning with Laplace Variational Recurrent Networkscited by 1
  34. 2025MetaTPT: Meta Test-time Prompt Tuning for Vision-Language Modelscited by 1
  35. 2026NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Trainingcited by 1
  36. 2021Learning Time-Invariant Reward Functions through Model-Based Inverse Reinforcement Learningcited by 0
  37. 2021Generating meta-learning tasks to evolve parametric loss for classification learningcited by 0
  38. 2022MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learningcited by 0

50 most cited of 60 All 60 (JSON)