解析高维不平衡分类的误差，给出可调参的理论模型。
An Analytical Model for Overparameterized Learning Under Class Imbalance
- 基于高维高斯混合模型构建测试误差闭式近似
- 揭示温度调整等方法如何降低标准交叉熵缺陷
- 适用于研究不平衡数据下的分类算法优化
我们研究高维高斯混合模型中的类别不平衡线性分类问题。针对多种实际学习方法（包括对数调整和类别相关温度），提出一种紧致的闭式误差近似。该近似使我们能够分析并调节这些方法，揭示其克服标准交叉熵最小化缺陷的机制与适用条件。我们在模拟数据及类别不平衡的CIFAR10、MNIST和FashionMNIST数据集上验证了理论结果。
原文摘要 · Abstract (English)
We study class-imbalanced linear classification in a high-dimensional Gaussian mixture model. We develop a tight, closed form approximation for the test error of several practical learning methods, including logit adjustment and class dependent temperature. Our approximation allows us to analytically tune and compare these methods, highlighting how and when they overcome the pitfalls of standard cross-entropy minimization. We test our theoretical findings on simulated data and imbalanced CIFAR10, MNIST and FashionMNIST datasets.
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。