Simultaneous and Sequential Inference of Pattern Recognition

• Activity Number: 585
• Type: Topic Contributed
• Date/Time: Wednesday, August 7, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistical Learning and Data Mining
• Author(s): Wenguang Sun*+
• Companies: University of Southern California
• Keywords: false discovery rate ; multiple testing ; sequential inference

Abstract

The accurate and reliable recovery of sparse signals in massive and complex data has been a fundamental question in many scientific fields. The discovery process usually involves an extensive search among a large number of hypotheses to separate signals of interest and also recognize their patterns. The situation can be described as finding needles of various shapes in a haystack. Despite the enormous progress on methodological work in data screening, pattern recognition and related fields, there have been little theoretical studies on the issues of optimality and error control in situations where a large number of decisions are made sequentially and simultaneously. We develop a compound decision theoretic framework and propose a new loss matrix approach to generalize the current multiple testing framework for error control in pattern recognition, by allowing more than two states of nature, sequential decision-making and new concepts of false positive rates in large-scale simultaneous inference.