A lower bound for the ELBO of the Bernoulli Variational Autoencoder

2020-03-26 · Robert Sicks, Ralf Korn, Stefanie Schwaar

We consider a variational autoencoder (VAE) for binary data. Our main innovations are an interpretable lower bound for its training objective, a modified initialization and architecture of such a VAE that leads to faster training, and a decision support for finding the appropriate dimension of the latent space via using a PCA. Numerical examples illustrate our theoretical result and the performance of the new architecture.

📄 PDF Abstract BibTeX arXiv:2003.11830

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…

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

USD Coin Customer Service Number +1-833-534-1729 설명 없음

Variational autoencoders trained with q-deformed lower bounds

2019-03-27 · ICLR Workshop DeepGenStruct 2019 · Septimia Sârbu, Luigi Malagò

Variational autoencoders (VAEs) have been successful at learning a low-dimensional manifold from high-dimensional data with complex dependencies. At their core, they consist of a powerful Bayesian probabilistic inference…

Variational Inference

Three Variations on Variational Autoencoders

2022-12-06 · R. I. Cukier

Variational autoencoders (VAEs) are one class of generative probabilistic latent-variable models designed for inference based on known data. We develop three variations on VAEs by introducing a second parameterized encod…

Decoder

Unbiased Implicit Variational Inference

2018-08-06 · Michalis K. Titsias, Francisco J. R. Ruiz

We develop unbiased implicit variational inference (UIVI), a method that expands the applicability of variational inference by defining an expressive variational family. UIVI considers an implicit variational distributio…

regression Variational Inference

ED-VAE: Entropy Decomposition of ELBO in Variational Autoencoders

2024-07-09 · Fotios Lygerakis, Elmar Rueckert

Traditional Variational Autoencoders (VAEs) are constrained by the limitations of the Evidence Lower Bound (ELBO) formulation, particularly when utilizing simplistic, non-analytic, or unknown prior distributions. These l…

InfoCatVAE: Representation Learning with Categorical Variational Autoencoders

2018-06-20 · Edouard Pineau, Marc Lelarge

This paper describes InfoCatVAE, an extension of the variational autoencoder that enables unsupervised disentangled representation learning. InfoCatVAE uses multimodal distributions for the prior and the inference networ…

Clustering Representation Learning