无需真实数据，用演化策略训练可迁移的分类损失函数。
Distribution-Free Pretraining of Classification Losses via Evolutionary Dynamics
- 用轻量网络参数化损失函数，在概率空间中通过合成数据预训练。
- 在CIFAR-10上替换交叉熵损失后，精度达竞争水平或更高。
- 引入混沌变异提升探索能力，收敛更快，效果优于传统方法。
我们提出进化动态损失（EDL），一种在概率空间中利用无限合成预测-标签对学习可迁移分类损失的框架，主预训练阶段无需访问真实样本。EDL将损失函数参数化为轻量级网络，并采用语义无关的排序一致性目标，对错误预测施加更大惩罚。为鲁棒探索损失函数空间，采用演化策略优化，并引入混沌变异以在噪声评估下增强探索能力。在使用ResNet主干网络的CIFAR-10实验中，EDL可作为交叉熵的即插即用替代品，实现竞争力或更优精度；消融实验表明，混沌变异相比标准高斯变异能加速收敛并提升合成预训练指标。
原文摘要 · Abstract (English)
We propose Evolutionary Dynamic Loss (EDL), a framework that learns a transferable classification loss in the probability space using unlimited synthetic prediction-label pairs, without accessing real samples during the main loss pretraining stage. EDL parameterizes the loss as a lightweight network and is trained with a semantics-free ranking-consistency objective that assigns larger penalties for more erroneous predictions. To robustly explore the space of loss functions, we optimize EDL via an evolutionary strategy and introduce chaotic mutation to improve exploration under noisy fitness evaluations. Experiments on CIFAR-10 with ResNet backbones show that EDL can serve as a drop-in replacement for cross-entropy and achieves competitive or improved accuracy, while ablation studies confirm that chaotic mutation yields faster convergence and better synthetic pretraining metrics than standard Gaussian mutation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。