paper-with-me

홈 › Papers

Denoising Criterion for Variational Auto-Encoding Framework

2015-11-19 · Daniel Jiwoong Im, Sungjin Ahn, Roland Memisevic, Yoshua Bengio

Denoising autoencoders (DAE) are trained to reconstruct their clean inputs with noise injected at the input level, while variational autoencoders (VAE) are trained with noise injected in their stochastic hidden layer, with a regularizer that encourages this noise injection. In this paper, we show that injecting noise both in input and in the stochastic hidden layer can be advantageous and we propose a modified variational lower bound as an improved objective function in this setup. When input is corrupted, then the standard VAE lower bound involves marginalizing the encoder conditional distribution over the input noise, which makes the training criterion intractable. Instead, we propose a modified training criterion which corresponds to a tractable bound when input is corrupted. Experimentally, we find that the proposed denoising variational autoencoder (DVAE) yields better average log-likelihood than the VAE and the importance weighted autoencoder on the MNIST and Frey Face datasets.

📄 PDF Abstract BibTeX arXiv:1511.06406

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Information Potential Auto-Encoders

2017-06-14 · Yan Zhang, Mete Ozay, Zhun Sun, Takayuki Okatani

In this paper, we suggest a framework to make use of mutual information as a regularization criterion to train Auto-Encoders (AEs). In the proposed framework, AEs are regularized by minimization of the mutual information…

Representation Learning

Denoising Variational Graph of Graphs Auto-Encoder for Predicting Structured Entity Interactions

2023-07-24 · IEEE Transactions on Knowledge and Data Engineering 2023 7 · PDF Han Chen, Hanchen Wang, Hongmei Chen, Ying Zhang 외

The interactions between structured entities play important roles in a wide range of applications such as chemistry, material science, biology, and medical science. Recently, graph-based methods have been exploited to ef…

Denoising

Improving Sampling from Generative Autoencoders with Markov Chains

2016-10-28 · Antonia Creswell, Kai Arulkumaran, Anil Anthony Bharath

We focus on generative autoencoders, such as variational or adversarial autoencoders, which jointly learn a generative model alongside an inference model. Generative autoencoders are those which are trained to softly enf…

Towards Deeper Understanding of Variational Autoencoding Models

2017-02-28 · Shengjia Zhao, Jiaming Song, Stefano Ermon

We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard evidence lower bound. We provide conditions under which they recover the data distribution and learn latent…

Information Constraints on Auto-Encoding Variational Bayes

2018-05-22 · NeurIPS 2018 12 · Romain Lopez, Jeffrey Regier, Michael. I. Jordan, Nir Yosef

Parameterizing the approximate posterior of a generative model with neural networks has become a common theme in recent machine learning research. While providing appealing flexibility, this approach makes it difficult t…