当前位置: X-MOL 学术J. Comput. Syst. Sci. › 论文详情
When are epsilon-nets small?
Journal of Computer and System Sciences ( IF 1.129 ) Pub Date : 2020-02-10 , DOI: 10.1016/j.jcss.2019.12.006
Andrey Kupavskii; Nikita Zhivotovskiy

Given a range space (X,R), where X is a set equipped with probability measure P, R ⊂ 2X is a family of measurable subsets, and ε>0, an ε-net is a subset of X in the support of P, which intersects each R ∈ R with P(R) ≥ε. In many situations the size of ε-nets depends on ε and on natural complexity measures. The aim of this paper is to give a systematic treatment of such complexity measures arising in Computational Geometry and Statistical Learning. As a byproduct, we obtain several new upper bounds on the sizes of ε-nets that improve the best known general guarantees. Some of our results deal with improvements in logarithmic factors, while others consider the regimes where ε-nets of size o(1) exist. ε. Inspired by results in Statistical Learning, we also give a short proof of the Haussler's upper bound on packing numbers.
更新日期:2020-02-10

 

全部期刊列表>>
向世界展示您的会议墙报和演示文稿
全球疫情及响应:BMC Medicine专题征稿
欢迎探索2019年最具下载量的化学论文
新版X-MOL期刊搜索和高级搜索功能介绍
化学材料学全球高引用
ACS材料视界
x-mol收录
自然科研论文编辑服务
南方科技大学
南方科技大学
西湖大学
中国科学院长春应化所于聪-4-8
复旦大学
课题组网站
X-MOL
深圳大学二维材料实验室张晗
中山大学化学工程与技术学院
试剂库存
天合科研
down
wechat
bug