Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Cost-Sensitive Learning via Deep Policy ERM
Lequn Wang, Qiantong Xu, Christopher De Sa, Thorsten Joachims
Feb 12, 2018 (modified: Jun 04, 2018)ICLR 2018 Workshop Submissionreaders: everyoneShow Bibtex
Abstract:Deep networks for classification are typically trained by maximizing the log likelihood of the training data. However, the conditional probabilities learned in this way are often not well-calibrated and are thus not well-suited for cost-sensitive learning where making different errors incurs different rewards or penalties. In this paper, we propose to directly train neural networks to optimize a cost sensitive loss via Empirical Risk Minimization (ERM). Empirical results show that, with proper initialization, ERM training with cost-sensitive loss outperforms maximum-likelihood training with various form of post-processing on a range of cost-sensitive classification tasks.