# Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment

arXiv: https://arxiv.org/abs/1905.05895 · HTML: https://mlsanity.com/paper/1905.05895/

## Key facts

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

## Built on by (most cited first, 30 of 33)

- [FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation](https://mlsanity.com/paper/2102.12867/) (2021)
- [Meta-learning PINN loss functions](https://mlsanity.com/paper/2107.05544/) (2021)
- [Customizing ML Predictions for Online Algorithms](https://mlsanity.com/paper/2205.08715/) (2022)
- [The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning](https://mlsanity.com/paper/2203.06498/) (2022)
- [Searching for Robustness: Loss Learning for Noisy Classification Tasks](https://mlsanity.com/paper/2103.00243/) (2021)
- [Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health](https://mlsanity.com/paper/2202.00916/) (2022)
- [FORML: Learning to Reweight Data for Fairness](https://mlsanity.com/paper/2202.01719/) (2022)
- [Score-oriented loss (SOL) functions](https://mlsanity.com/paper/2103.15522/) (2021)
- [Training Over-parameterized Models with Non-decomposable Objectives](https://mlsanity.com/paper/2107.04641/) (2021)
- [MetricOpt: Learning to Optimize Black-Box Evaluation Metrics](https://mlsanity.com/paper/2104.10631/) (2021)
- [CCMN: A General Framework for Learning with Class-Conditional Multi-Label Noise](https://mlsanity.com/paper/2105.07338/) (2021)
- [Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks](https://mlsanity.com/paper/2107.02378/) (2021)
- [Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning](https://mlsanity.com/paper/2209.08907/) (2022)
- [Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the Wild](https://mlsanity.com/paper/2208.07522/) (2022)
- [Optimizing Black-box Metrics with Iterative Example Weighting](https://mlsanity.com/paper/2102.09492/) (2021)
- [Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics](https://mlsanity.com/paper/2304.14738/) (2023)
- [DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning](https://mlsanity.com/paper/2305.07892/) (2023)
- [Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning](https://mlsanity.com/paper/2106.03279/) (2021)
- [Improve Noise Tolerance of Robust Loss via Noise-Awareness](https://mlsanity.com/paper/2301.07306/) (2023)
- [A comprehensive theoretical framework for the optimization of neural networks classification performance with respect to weighted metrics](https://mlsanity.com/paper/2305.13472/) (2023)
- [Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks](https://mlsanity.com/paper/2107.00364/) (2021)
- [OWAdapt: An adaptive loss function for deep learning using OWA operators](https://mlsanity.com/paper/2305.19443/) (2023)
- [L2T-DLN: Learning to Teach with Dynamic Loss Network](https://mlsanity.com/paper/2310.19313/) (2023)
- [DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents](https://mlsanity.com/paper/2510.19336/) (2025)
- [Reinforcement Teaching](https://mlsanity.com/paper/2204.11897/) (2022)
- [Fast and Efficient Local Search for Genetic Programming Based Loss Function Learning](https://mlsanity.com/paper/2403.00865/) (2024)
- [Aligning the Evaluation of Probabilistic Predictions with Downstream Value](https://mlsanity.com/paper/2508.18251/) (2025)
- [Implicit Training of Energy Model for Structure Prediction](https://mlsanity.com/paper/2211.11649/) (2022)
- [Label Budget Allocation in Multi-Task Learning](https://mlsanity.com/paper/2308.12949/) (2023)
- [Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data](https://mlsanity.com/paper/2501.07346/) (2025)

## 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.