# AM-LFS: AutoML for Loss Function Search

arXiv: https://arxiv.org/abs/1905.07375 · HTML: https://mlsanity.com/paper/1905.07375/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2019.

## Built on by (most cited first, 29 of 29)

- [ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding](https://mlsanity.com/paper/2203.10886/) (2022)
- [PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions](https://mlsanity.com/paper/2204.12511/) (2022)
- [Automated Self-Supervised Learning for Graphs](https://mlsanity.com/paper/2106.05470/) (2021)
- [Contrastive Multimodal Fusion with TupleInfoNCE](https://mlsanity.com/paper/2107.02575/) (2021)
- [AutoLoss: Automated Loss Function Search in Recommendations](https://mlsanity.com/paper/2106.06713/) (2021)
- [Swift Sampler: Efficient Learning of Sampler by 10 Parameters](https://mlsanity.com/paper/2410.05578/) (2024)
- [SphereFace Revived: Unifying Hyperspherical Face Recognition](https://mlsanity.com/paper/2109.05565/) (2021)
- [Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search](https://mlsanity.com/paper/2102.04700/) (2021)
- [AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks](https://mlsanity.com/paper/2103.14026/) (2021)
- [Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization](https://mlsanity.com/paper/2201.08613/) (2022)
- [Reinforcement Learning with Automated Auxiliary Loss Search](https://mlsanity.com/paper/2210.06041/) (2022)
- [AWSnet: An Auto-weighted Supervision Attention Network for Myocardial Scar and Edema Segmentation in Multi-sequence Cardiac Magnetic Resonance Images](https://mlsanity.com/paper/2201.05344/) (2022)
- [AutoLossGen: Automatic Loss Function Generation for Recommender Systems](https://mlsanity.com/paper/2204.13160/) (2022)
- [Toward a Better Understanding of Loss Functions for Collaborative Filtering](https://mlsanity.com/paper/2308.06091/) (2023)
- [LPZero: Language Model Zero-cost Proxy Search from Zero](https://mlsanity.com/paper/2410.04808/) (2024)
- [Learn Fine-grained Adaptive Loss for Multiple Anatomical Landmark Detection in Medical Images](https://mlsanity.com/paper/2105.09124/) (2021)
- [Efficient Non-Parametric Optimizer Search for Diverse Tasks](https://mlsanity.com/paper/2209.13575/) (2022)
- [Learning image quality assessment by reinforcing task amenable data selection](https://mlsanity.com/paper/2102.07615/) (2021)
- [Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering](https://mlsanity.com/paper/2202.13140/) (2022)
- [Meta-Learning Adaptive Loss Functions](https://mlsanity.com/paper/2301.13247/) (2023)
- [Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detection](https://mlsanity.com/paper/2304.12161/) (2023)
- [DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning](https://mlsanity.com/paper/2305.07892/) (2023)
- [Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search](https://mlsanity.com/paper/2111.05063/) (2021)
- [Towards Robust Face Recognition with Comprehensive Search](https://mlsanity.com/paper/2208.13600/) (2022)
- [Improve Noise Tolerance of Robust Loss via Noise-Awareness](https://mlsanity.com/paper/2301.07306/) (2023)
- [HLIC: Harmonizing Optimization Metrics in Learned Image Compression by Reinforcement Learning](https://mlsanity.com/paper/2109.14863/) (2021)
- [Next Generation Loss Function for Image Classification](https://mlsanity.com/paper/2404.12948/) (2024)
- [SIRe-Networks: Convolutional Neural Networks Architectural Extension for Information Preservation via Skip/Residual Connections and Interlaced Auto-Encoders](https://mlsanity.com/paper/2110.02776/) (2021)
- [EvoRank: LLM-Guided Evolution of Multi-Objective Learning-to-Rank Pipelines](https://mlsanity.com/paper/2609.22196/) (2026)

## Abstract (arXiv)

Designing an effective loss function plays an important role in visual analysis. Most existing loss function designs rely on hand-crafted heuristics that require domain experts to explore the large design space, which is usually sub-optimal and time-consuming. In this paper, we propose AutoML for Loss Function Search (AM-LFS) which leverages REINFORCE to search loss functions during the training process. The key contribution of this work is the design of search space which can guarantee the generalization and transferability on different vision tasks by including a bunch of existing prevailing loss functions in a unified formulation. We also propose an efficient optimization framework which can dynamically optimize the parameters of loss function's distribution during training. Extensive experimental results on four benchmark datasets show that, without any tricks, our method outperforms existing hand-crafted loss functions in various computer vision tasks.