Affordable Access

Max-margin Deep Generative Models

Authors
  • Li, Chongxuan
  • Zhu, Jun
  • Shi, Tianlin
  • Zhang, Bo
Type
Preprint
Publication Date
Dec 14, 2015
Submission Date
Apr 26, 2015
Identifiers
arXiv ID: 1504.06787
Source
arXiv
License
Yellow
External links

Abstract

Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability. However, little work has been done on examining or empowering the discriminative ability of DGMs on making accurate predictions. This paper presents max-margin deep generative models (mmDGMs), which explore the strongly discriminative principle of max-margin learning to improve the discriminative power of DGMs, while retaining the generative capability. We develop an efficient doubly stochastic subgradient algorithm for the piecewise linear objective. Empirical results on MNIST and SVHN datasets demonstrate that (1) max-margin learning can significantly improve the prediction performance of DGMs and meanwhile retain the generative ability; and (2) mmDGMs are competitive to the state-of-the-art fully discriminative networks by employing deep convolutional neural networks (CNNs) as both recognition and generative models.

Report this publication

Statistics

Seen <100 times