报告题目：Atomic Representation-based Classification: Algorithm and Theory
报 告 人：李落清 教授（湖北大学）
报告时间：2019年10月22日（星期二）上午10：30
报告地点：磬苑校区理工D楼318室
主办单位：安徽大学计算机科学与技术学院
欢迎各位老师、同学届时前往！
科学技术处
2019年10月21日
报告摘要:
Representation-based classification (RC) methods such as sparse RC (SRC) have attracted great interest in pattern recognition recently. In this talk, we introduce a new condition called atomic classification condition (ACC), which reveals important geometric insights for the theory of ARC. We establish the theoretical guarantees for a general unified framework termed as atomic representation-based classification (ARC), which includes most RC methods as special cases. We show that under such condition ARC is provably effective in correctly recognizing any new test sample, even corrupted with noise. Numerical results are provided to validate and complement our theoretical analysis of ARC and its important special cases for both noiseless and noisy test data.