In this letter, we consider multiple statistical classification problem where a sequence of n independent and identically distributed observations, that are generated by one of M discrete sources, need to be classified. The source distributions are not known, however one has access to labeled training sequences, of length N, from each source. We consider the case where the unknown source distributions are estimated from the training sequences, then the estimates are used as nominal distributions in a robust hypothesis test. Specifically, we consider the robust DGL test due to Devroye et al. and provide non-asymptotic exponential bounds, that are functions of N{n, on the error probability of classification.

中文翻译：

---

通过稳健假设检验的统计分类

在这封信中，我们考虑多个统计分类问题，其中需要对由 M 个离散源之一生成的 n 个独立且同分布的观测值序列进行分类。源分布未知，但是可以访问来自每个源的标记训练序列，长度为 N。我们考虑从训练序列估计未知源分布的情况，然后将估计值用作稳健假设检验中的名义分布。具体来说，我们考虑了 Devroye 等人提出的强大的 DGL 测试。并提供非渐近指数边界，即分类错误概率的 N{n 函数。