Conditional Generative Moment-Matching Networks
arXiv:1606.04218
Abstract
Maximum mean discrepancy (MMD) has been successfully applied to learn deep generative models for characterizing a joint distribution of variables via kernel mean embedding. In this paper, we present conditional generative moment- matching networks (CGMMN), which learn a conditional distribution given some input variables based on a conditional maximum mean discrepancy (CMMD) criterion. The learning is performed by stochastic gradient descent with the gradient calculated by back-propagation. We evaluate CGMMN on a wide range of tasks, including predictive modeling, contextual generation, and Bayesian dark knowledge, which distills knowledge from a Bayesian model by learning a relatively small CGMMN student network. Our results demonstrate competitive performance in all the tasks.
arXiv comment12 pages
References in corpus (10)
- Auto-Encoding Variational Bayes
- Conditional Generative Adversarial Nets
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
- Generative Moment Matching Networks
- Sum-Product Networks: A New Deep Architecture
- Bayesian Dark Knowledge
- Attribute2Image: Conditional Image Generation from Visual Attributes
- Max-margin Deep Generative Models
- Learning to Generate Chairs, Tables and Cars with Convolutional Networks
Cited by in corpus (14)
- Learning Target Domain Specific Classifier for Partial Domain Adaptation
- Conditional Sig-Wasserstein GANs for Time Series Generation
- Statistical Inference for Generative Models with Maximum Mean Discrepancy
- Domain Adaptation as a Problem of Inference on Graphical Models
- A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings
- Learning Kernel for Conditional Moment-Matching Discrepancy-based Image Classification
- Measuring the Discrepancy between Conditional Distributions: Methods, Properties and Applications
- Sampling-based speech parameter generation using moment-matching networks
- When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights
- Rescuing neural spike train models from bad MLE
- Quantile-Quantile Embedding for Distribution Transformation and Manifold Embedding with Ability to Choose the Embedding Distribution
- Max-Margin Deep Generative Models for (Semi-)Supervised Learning
- Irregular Convolutional Auto-Encoder on Point Clouds
- Label-Removed Generative Adversarial Networks Incorporating with K-Means