发表机构
University of Bristol; Indian Institute of Science(布里斯托大学; 印度科学学院)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
研究从\(O(\log K)\)个简单二元分类器组合构建\(K\)类分类器的问题,当二元分类器为超平面时,在高斯设置下得出性能界限,并通过模拟实验验证理论结果。
AI 中文摘要
我们考虑从\(O(\log K)\)个简单二元分类器组合构建\(K\)类分类器的问题,这是一种以分布式方式构建复杂分类器的自然范式,每个代理执行相对简单的任务。当相应的二元分类器为超平面时,我们研究这种分类器的基本性能限制。在一个程式化的高斯设置中,其中\(K\)个类中心是\(\mathbb R^d\)中的独立高斯点,并且观测值被高斯噪声破坏,我们在几个解码和维度范围内得出了明确的性能界限。广泛的模拟实验对所提出的理论结果提供了有力的实证验证。
英文摘要
We consider the problem of constructing a $K$-class classifier from the combination of $O(\log K)$ simple binary classifiers -- this is a natural paradigm to construct a sophisticated classifier in a distributed manner with each agent performing a relatively straightforward task. We study the fundamental performance limits of such a classifier when the corresponding binary classifiers are hyperplanes. For a stylized Gaussian setting where the $K$ class centers are independent Gaussian points in $\mathbb R^d$ and the observations are corrupted by Gaussian noise, we derive explicit performance bounds across several decoding and dimensional regimes. Extensive simulation experiments provide strong empirical validation of the presented theoretical results.