S
Shengjia Zhao
Researcher at Stanford University
Publications - 54
Citations - 1996
Shengjia Zhao is an academic researcher from Stanford University. The author has contributed to research in topics: Computer science & Latent variable. The author has an hindex of 17, co-authored 47 publications receiving 1433 citations. Previous affiliations of Shengjia Zhao include Tsinghua University.
Papers
More filters
Posted Content
InfoVAE: Information Maximizing Variational Autoencoders
TL;DR: It is shown that this model can significantly improve the quality of the variational posterior and can make effective use of the latent features regardless of the flexibility of the decoding distribution, and it is demonstrated that the models outperform competing approaches on multiple performance metrics.
Journal ArticleDOI
InfoVAE: Balancing Learning and Inference in Variational Autoencoders
TL;DR: It is shown that the proposed Info-VAE model can significantly improve the quality of the variational posterior and can make effective use of the latent features regardless of the flexibility of the decoding distribution.
Proceedings Article
Learning Controllable Fair Representations
TL;DR: Exploiting duality, this work introduces a method that optimizes the model parameters as well as the expressiveness-fairness trade-off and achieves higher expressiveness at a lower computational cost.
Posted Content
Towards Deeper Understanding of Variational Autoencoding Models
TL;DR: A new sequential VAE model that can generate sharp samples on the LSUN image dataset based on pixel-wise reconstruction loss is proposed, and an optimization criterion is proposed that encourages unsupervised learning of informative latent features.
Proceedings Article
Learning Hierarchical Features from Deep Generative Models
TL;DR: It is proved that hierarchical latent variable models do not take advantage of the hierarchical structure when trained with some existing variational methods, and some limitations on the kind of features existing models can learn are provided.