Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model. Existing techniques for loss function learning have shown promising results, often improving a model's training dynamics and final inference performance. However, a significant limitation of these techniques is that the loss functions are meta-learned in an offline fashion, where the meta-objective only considers the very first few steps of training, which is a significantly shorter time horizon than the one typically used for training deep neural networks. This causes significant bias towards loss functions that perform well at the very start of training but perform poorly at the end of training. To address this issue we propose a new loss function learning technique for adaptively updating the loss function online after each update to the base model parameters. The experimental results show that our proposed method consistently outperforms the cross-entropy loss and offline loss function learning techniques on a diverse range of neural network architectures and datasets.

翻译：损失函数学习是一种新的元学习范式，旨在自动化机器学习模型中损失函数设计这一关键任务。现有的损失函数学习技术已展现出良好的效果，通常能改善模型的训练动态和最终推理性能。然而，这些技术存在一个显著局限：损失函数以离线方式进行元学习，其元目标仅考虑训练最初的少数几步，这远短于深度神经网络通常使用的训练时长。这导致模型严重偏向于在训练初期表现良好、但在训练后期表现欠佳的损失函数。为解决该问题，我们提出了一种新的损失函数学习技术，可在基础模型参数每次更新后在线自适应调整损失函数。实验结果表明，在多种神经网络架构和数据集上，我们提出的方法始终优于交叉熵损失和离线损失函数学习技术。