中文
相关论文

相关论文: Beyond Diagonal Covariance: Flexible Posterior VAE…

200 篇论文

In this paper, we study two aspects of the variational autoencoder (VAE): the prior distribution over the latent variables and its corresponding posterior. First, we decompose the learning of VAEs into layerwise density estimation, and…

Variational autoencoders (VAE) often use Gaussian or category distribution to model the inference process. This puts a limit on variational learning because this simplified assumption does not match the true posterior distribution, which is…

机器学习 · 计算机科学 2017-02-28 Ke Sun , Xiangliang Zhang

The Variational Autoencoder (VAE) is a powerful framework for learning probabilistic latent variable generative models. However, typical assumptions on the approximate posterior distribution of the encoder and/or the prior, seriously…

机器学习 · 计算机科学 2020-07-13 Ifigeneia Apostolopoulou , Elan Rosenfeld , Artur Dubrawski

Variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying…

机器学习 · 计算机科学 2019-10-08 Bin Dai , Yu Wang , John Aston , Gang Hua , David Wipf

Variational auto-encoders (VAE) are scalable and powerful generative models. However, the choice of the variational posterior determines tractability and flexibility of the VAE. Commonly, latent variables are modeled using the normal…

机器学习 · 计算机科学 2017-01-30 Jakub M. Tomczak , Max Welling

As one of the most popular generative models, Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. However, when the decoder network is sufficiently expressive, VAE may lead…

机器学习 · 计算机科学 2021-10-26 Dazhong Shen , Chuan Qin , Chao Wang , Hengshu Zhu , Enhong Chen , Hui Xiong

Learning latent representations that are simultaneously expressive, geometrically well-structured, and reliably calibrated remains a central challenge for Variational Autoencoders (VAEs). Standard VAEs typically assume a diagonal Gaussian…

机器学习 · 计算机科学 2025-12-02 Mehmet Can Yavuz

Variational autoencdoers (VAE) are a popular approach to generative modelling. However, exploiting the capabilities of VAEs in practice can be difficult. Recent work on regularised and entropic autoencoders have begun to explore the…

机器学习 · 计算机科学 2022-03-02 Gregory A. Daly , Jonathan E. Fieldsend , Gavin Tabor

Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this…

机器学习 · 计算机科学 2020-06-01 Partha Ghosh , Mehdi S. M. Sajjadi , Antonio Vergari , Michael Black , Bernhard Schölkopf

In just three years, Variational Autoencoders (VAEs) have emerged as one of the most popular approaches to unsupervised learning of complicated distributions. VAEs are appealing because they are built on top of standard function…

机器学习 · 统计学 2021-01-05 Carl Doersch

Invertible flow-based generative models are an effective method for learning to generate samples, while allowing for tractable likelihood computation and inference. However, the invertibility requirement restricts models to have the same…

机器学习 · 计算机科学 2020-02-21 Abhishek Kumar , Ben Poole , Kevin Murphy

Although variational autoencoders (VAEs) represent a widely influential deep generative model, many aspects of the underlying energy function remain poorly understood. In particular, it is commonly believed that Gaussian encoder/decoder…

机器学习 · 计算机科学 2019-10-31 Bin Dai , David Wipf

Variational autoencoders (VAE) are a powerful and widely-used class of models to learn complex data distributions in an unsupervised fashion. One important limitation of VAEs is the prior assumption that latent sample representations are…

机器学习 · 计算机科学 2018-11-27 Francesco Paolo Casale , Adrian V Dalca , Luca Saglietti , Jennifer Listgarten , Nicolo Fusi

Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional latent space learned in an unsupervised manner. In the original VAE model, the input data…

机器学习 · 计算机科学 2022-07-05 Laurent Girin , Simon Leglaive , Xiaoyu Bie , Julien Diard , Thomas Hueber , Xavier Alameda-Pineda

Variational autoencoder (VAE) is a very successful generative model whose key element is the so called amortized inference network, which can perform test time inference using a single feed forward pass. Unfortunately, this comes at the…

机器学习 · 计算机科学 2021-02-08 Minyoung Kim , Vladimir Pavlovic

Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling. However, VAEs are also more and more outperformed by competing models such as…

机器学习 · 计算机科学 2021-07-01 Antoine Wehenkel , Gilles Louppe

Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the…

机器学习 · 计算机科学 2019-12-02 Le Fang , Chunyuan Li , Jianfeng Gao , Wen Dong , Changyou Chen

The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong…

机器学习 · 计算机科学 2016-11-08 Yuri Burda , Roger Grosse , Ruslan Salakhutdinov

Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed latent space from…

机器学习 · 计算机科学 2025-05-16 Alan Jeffares , Liyuan Liu

Variational auto-encoders (VAEs) are a popular and powerful deep generative model. Previous works on VAEs have assumed a factorized likelihood model, whereby the output uncertainty of each pixel is assumed to be independent. This…

机器学习 · 统计学 2026-05-14 Gara Dorta , Sara Vicente , Lourdes Agapito , Neill D. F. Campbell , Ivor Simpson
‹ 上一页 1 2 3 10 下一页 ›