|
主讲人 |
Rui Pan |
简介 |
<p>Abstract：</p>
<div>This paper is concerned with the problem of feature screening for multi-class linear</div>
<div>discriminant analysis under ultrahigh dimensional setting. We allow the number of</div>
<div>classes to be relatively large. As a result, the total number of relevant features is</div>
<div>larger than usual. This makes the related classification problem much more</div>
<div>challenging than the conventional one, where the number of classes is small (very</div>
<div>often two). To solve the problem, we propose a novel pairwise sure independence</div>
<div>screening method for linear discriminant analysis with an ultrahigh dimensional</div>
<div>predictor. The proposed procedure is directly applicable to the situation with many</div>
<div>classes. We further prove that the proposed method is screening consistent.</div>
<div>Simulation studies are conducted to assess the finite sample performance of the new</div>
<div>procedure. We also demonstrate the proposed methodology via an empirical analysis</div>
<div>of a real life example on handwritten Chinese character recognition.</div>
<div> </div>
<div>Keywords: Multi-class Linear Discriminant Analysis; Pairwise Sure Independence</div>
<div>Screening; Sure Independence Screening; Strong Screening Consistency.</div> |
|
主讲人简介 |
<div>Assitant Professor</div>
<div> </div>
<div>School of Statistics and Mathematics</div>
<p> </p>
<div>Central University of Finance and Economics</div>
<p><a href="/EventsMgr/Upload/File/2015/4/2015041611500968.pdf">Prof. Rui Pan' CV</a></p> |
期数 |
厦门大学高级计量经济学与统计学系列讲座2015春季学期第三讲（总第58讲） |
