arXiv:2503.14045stat.MLcs.LG2025-03被引 2

基于L2风险最小化,实现随机扩散路径的多分类,可达到快速收敛速率。

Empirical risk minimization algorithm for multiclass classification of S.D.E. paths

  • 通过最小化L2风险构建多分类算法,利用漂移函数区分类别。
  • 在边缘假设下,预测器达到快速收敛速率,理论性能更优。
  • 适用于具有共同扩散系数、不同漂移函数的路径分类任务。

我们研究了基于随机扩散路径的多分类问题,假设各类别由不同的漂移函数区分,而扩散系数在所有类别中保持一致。在此设定下,提出一种基于最小化L2风险的分类算法,并建立了所得预测器的收敛速率。特别地,在引入边缘假设的前提下,证明该方法可实现快速收敛速率。最后,通过模拟实验验证了算法的数值表现。

原文摘要 · Abstract (English)

We address the multiclass classification problem for stochastic diffusion paths, assuming that the classes are distinguished by their drift functions, while the diffusion coefficient remains common across all classes. In this setting, we propose a classification algorithm that relies on the minimization of the L 2 risk. We establish rates of convergence for the resulting predictor. Notably, we introduce a margin assumption under which we show that our procedure can achieve fast rates of convergence. Finally, a simulation study highlights the numerical performance of our classification algorithm.

多分类随机过程风险最小化

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。