简单的弱核心集对于不可分解分类测量

Dec, 2023

简单的弱核心集对于不可分解分类测量

Simple Weak Coresets for Non-Decomposable Classification Measures

Jayesh Malaviya, Anirban Dasgupta, Rachit Chhaya

TL;DR考虑监督分类问题和非可分解评估指标，研究基于分层均匀采样的coresets在实证性能与理论保证方面表现优秀，特别针对F1得分和Matthews相关系数这两个广泛使用且难以优化的非可分解目标函数，证明均匀coresets达到了coreset大小的下界，并且在实验表现上与“更聪明”的coreset构建策略相当。

Abstract

While coresets have been growing in terms of their application, barring few exceptions, they have mostly been limited to unsupervised settings. We consider supervised classification problems, and non-decomposable