Timezone: »
Poster
Prediction Rule Reshaping
Matt Bonakdarpour · Sabyasachi Chatterjee · Rina Barber · John Lafferty
Two methods are proposed for high-dimensional shape-constrained regression and classification. These methods reshape pre-trained prediction rules to satisfy shape constraints like monotonicity and convexity. The first method can be applied to any pre-trained prediction rule, while the second method deals specifically with random forests. In both cases, efficient algorithms are developed for computing the estimators, and experiments are performed to demonstrate their performance on four datasets. We find that reshaping methods enforce shape constraints without compromising predictive accuracy.
Author Information
Matt Bonakdarpour (University of Chicago)
Sabyasachi Chatterjee (Sabyasachi Chatterjee)
Rina Barber
John Lafferty (Yale University)
Related Events (a corresponding poster, oral, or spotlight)
-
2018 Oral: Prediction Rule Reshaping »
Thu Jul 12th 12:00 -- 12:10 PM Room A6
More from the Same Authors
-
2018 Poster: Distributed Nonparametric Regression under Communication Constraints »
Yuancheng Zhu · John Lafferty -
2018 Oral: Distributed Nonparametric Regression under Communication Constraints »
Yuancheng Zhu · John Lafferty