Timezone: »

Selective Inference for Sparse High-Order Interaction Models
Shinya Suzumura · Kazuya Nakagawa · Yuta Umezu · Koji Tsuda · Ichiro Takeuchi

Mon Aug 07 11:24 PM -- 11:42 PM (PDT) @ C4.4
Finding statistically significant high-order interactions in predictive modeling is important but challenging task because the possible number of high-order interactions is extremely large (e.g., $> 10^{17}$). In this paper we study feature selection and statistical inference for sparse high-order interaction models. Our main contribution is to extend recently developed selective inference framework for linear models to high-order interaction models by developing a novel algorithm for efficiently characterizing the selection event for the selective inference of high-order interactions. We demonstrate the effectiveness of the proposed algorithm by applying it to an HIV drug response prediction problem.

Author Information

Shinya Suzumura (Nagoya Institute of Technology)
Kazuya Nakagawa (Nagoya Institute of Technology)
Yuta Umezu (Nagoya Institute of Technology)
Koji Tsuda (University of Tokyo / RIKEN)
Ichiro Takeuchi (Nagoya Institute of Technology / RIKEN)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors