paper-with-me

Papers

InfoVAE: Information Maximizing Variational Autoencoders

2017-06-07 · Shengjia Zhao, Jiaming Song, Stefano Ermon

A key advance in learning generative models is the use of amortized inference distributions that are jointly trained with the models. We find that existing training objectives for variational autoencoders can lead to inaccurate amortized inference distributions and, in some cases, improving the objective provably degrades the inference quality. In addition, it has been observed that variational autoencoders tend to ignore the latent variables when combined with a decoding distribution that is too flexible. We again identify the cause in existing training criteria and propose a new class of objectives (InfoVAE) that mitigate these problems. We show that our 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. Through extensive qualitative and quantitative analyses, we demonstrate that our models outperform competing approaches on multiple performance metrics.

📄 PDF Abstract BibTeX arXiv:1706.02262

Code (6)

AntixK/PyTorch-VAE pytorch
Saswatm123/MMD-VAE pytorch
clementchadebec/benchmark_VAE pytorch
ema-marconato/glancenet pytorch
zacheberhart/Convolutional-Disentangled-Variational-Autoencoder pytorch
zacheberhart/Maximum-Mean-Discrepancy-Variational-Autoencoder tf

Similar Papers 제목 키워드 기반

InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihood

2021-07-09 · Fei Ye, Adrian G. Bors

Learning disentangled and interpretable representations is an important step towards accomplishing comprehensive data representations on the manifold. In this paper, we propose a novel representation learning algorithm w…

Representation Learning

Learning Discrete Structured Representations by Adversarially Maximizing Mutual Information

2020-04-08 · ICML 2020 1 · Karl Stratos, Sam Wiseman

We propose learning discrete structured representations from unlabeled data by maximizing the mutual information between a structured latent variable and a target variable. Calculating mutual information is intractable i…

The Information-Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Modeling

2018-01-01 · ICLR 2018 1 · Shengjia Zhao, Jiaming Song, Stefano Ermon

A variety of learning objectives have been recently proposed for training generative models. We show that many of them, including InfoGAN, ALI/BiGAN, ALICE, CycleGAN, VAE, $\beta$-VAE, adversarial autoencoders, AVB, and …

Latent Representation Learning from 3D Brain MRI for Interpretable Prediction in Multiple Sclerosis

2025-09-28 · Trinh Ngoc Huynh, Nguyen Duc Kien, Nguyen Hai Anh, Dinh Tran Hiep 외 arxiv

We present InfoVAE-Med3D, a latent-representation learning approach for 3D brain MRI that targets interpretable biomarkers of cognitive decline. Standard statistical models and shallow machine learning often lack power, …

Representation Learning

Learning Representations by Maximizing Mutual Information in Variational Autoencoders

2019-12-21 · Ali Lotfi Rezaabad, Sriram Vishwanath

Variational autoencoders (VAEs) have ushered in a new era of unsupervised learning methods for complex distributions. Although these techniques are elegant in their approach, they are typically not useful for representat…

Representation Learning