Max-margin Deep Generative Models

04/26/2015
by   Chongxuan Li, et al.
0

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.

READ FULL TEXT

page 7

page 8

page 12

research
11/22/2016

Max-Margin Deep Generative Models for (Semi-)Supervised Learning

Deep generative models (DGMs) are effective on learning multilayered rep...
research
04/21/2023

Matching-based Data Valuation for Generative Model

Data valuation is critical in machine learning, as it helps enhance mode...
research
09/19/2011

Learning Discriminative Metrics via Generative Models and Kernel Learning

Metrics specifying distances between data points can be learned in a dis...
research
04/18/2018

Deep Generative Networks For Sequence Prediction

This thesis investigates unsupervised time series representation learnin...
research
11/12/2017

Medical Diagnosis From Laboratory Tests by Combining Generative and Discriminative Learning

A primary goal of computational phenotype research is to conduct medical...
research
04/01/2020

A theory of independent mechanisms for extrapolation in generative models

Deep generative models reproduce complex empirical data but cannot extra...
research
12/23/2015

A Deep Generative Deconvolutional Image Model

A deep generative model is developed for representation and analysis of ...

Please sign up or login with your details

Forgot password? Click here to reset