mlsanityData to 14 Oct 2026

Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment

arXiv 1905.05895 ↗First posted 15 May 2019cs.LG cs.CV stat.MLcited by 33

Not on the map. Why?

Abstract (arXiv)

In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to directly optimize the evaluation metric. We propose a sample efficient reinforcement learning approach for adapting the loss dynamically during training. We empirically show how this formulation improves performance by simultaneously optimizing the evaluation metric and smoothing the loss landscape. We verify our method in metric learning and classification scenarios, showing considerable improvements over the state-of-the-art on a diverse set of tasks. Importantly, our method is applicable to a wide range of loss functions and evaluation metrics. Furthermore, the learned policies are transferable across tasks and data, demonstrating the versatility of the method.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 8; 2023: 7; 2024: 1; 2025: 4; 2026: 2.

33 papers.

Sort:

By area:

  1. 2021FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentationcited by 76
  2. 2021Meta-learning PINN loss functionscited by 51
  3. 2022Customizing ML Predictions for Online Algorithmscited by 21
  4. 2022The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learningcited by 17
  5. 2021Searching for Robustness: Loss Learning for Noisy Classification Taskscited by 13
  6. 2022Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Healthcited by 12
  7. 2022FORML: Learning to Reweight Data for Fairnesscited by 12
  8. 2021Score-oriented loss (SOL) functionscited by 11
  9. 2021Training Over-parameterized Models with Non-decomposable Objectivescited by 11
  10. 2021MetricOpt: Learning to Optimize Black-Box Evaluation Metricscited by 9
  11. 2021CCMN: A General Framework for Learning with Class-Conditional Multi-Label Noisecited by 9
  12. 2021Learning an Explicit Hyperparameter Prediction Function Conditioned on Taskscited by 9
21 more
  1. 2022Learning Symbolic Model-Agnostic Loss Functions via Meta-Learningcited by 9
  2. 2022Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the Wildcited by 7
  3. 2021Optimizing Black-box Metrics with Iterative Example Weightingcited by 6
  4. 2023Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metricscited by 4
  5. 2023DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learningcited by 4
  6. 2021Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learningcited by 3
  7. 2023Improve Noise Tolerance of Robust Loss via Noise-Awarenesscited by 3
  8. 2023A comprehensive theoretical framework for the optimization of neural networks classification performance with respect to weighted metricscited by 3
  9. 2021Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottleneckscited by 2
  10. 2023OWAdapt: An adaptive loss function for deep learning using OWA operatorscited by 2
  11. 2023L2T-DLN: Learning to Teach with Dynamic Loss Networkcited by 2
  12. 2025DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agentscited by 2
  13. 2022Reinforcement Teachingcited by 1
  14. 2024Fast and Efficient Local Search for Genetic Programming Based Loss Function Learningcited by 1
  15. 2025Aligning the Evaluation of Probabilistic Predictions with Downstream Valuecited by 1
  16. 2022Implicit Training of Energy Model for Structure Predictioncited by 0
  17. 2023Label Budget Allocation in Multi-Task Learningcited by 0
  18. 2025Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Datacited by 0
  19. 2025An Efficient Plugin Method for Metric Optimization of Black-Box Modelscited by 0
  20. 2026Don't stop me now: How Validation Criteria Affect Checkpoint Selection and Early Stoppingcited by 0
  21. 2026Distribution-Free Pretraining of Classification Losses via Evolutionary Dynamicscited by 0