中文
相关论文

相关论文: The Neglected Sibling: Isotropic Gaussian Posterio…

200 篇论文

Deep generative models have achieved impressive success in recent years. Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families for generative model learning, have largely been considered as two…

机器学习 · 计算机科学 2018-07-12 Zhiting Hu , Zichao Yang , Ruslan Salakhutdinov , Eric P. Xing

The recently proposed identifiable variational autoencoder (iVAE) framework provides a promising approach for learning latent independent components (ICs). iVAEs use auxiliary covariates to build an identifiable generation structure from…

机器学习 · 统计学 2022-10-17 Young-geun Kim , Ying Liu , Xuexin Wei

Variational Autoencoders (VAEs) are powerful generative models capable of learning compact latent representations. However, conventional VAEs often generate relatively blurry images due to their assumption of an isotropic Gaussian latent…

计算机视觉与模式识别 · 计算机科学 2025-04-21 Andrew Kiruluta

Generative models have recently gained increasing attention in image generation and editing tasks. However, they often lack a direct connection to object geometry, which is crucial in sensitive domains such as computational anatomy,…

图形学 · 计算机科学 2025-04-14 Nian Wu , Nivetha Jayakumar , Jiarui Xing , Miaomiao Zhang

Variational autoencoders (VAEs) and generative adversarial networks (GANs) enjoy an intuitive connection to manifold learning: in training the decoder/generator is optimized to approximate a homeomorphism between the data distribution and…

机器学习 · 计算机科学 2020-08-28 Henry Li , Ofir Lindenbaum , Xiuyuan Cheng , Alexander Cloninger

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

Deep Gaussian processes (DGPs) are increasingly popular as predictive models in machine learning (ML) for their non-stationary flexibility and ability to cope with abrupt regime changes in training data. Here we explore DGPs as surrogates…

统计方法学 · 统计学 2021-08-27 Annie Sauer , Robert B. Gramacy , David Higdon

We introduce a variational Bayesian neural network where the parameters are governed via a probability distribution on random matrices. Specifically, we employ a matrix variate Gaussian \cite{gupta1999matrix} parameter posterior…

机器学习 · 统计学 2016-06-24 Christos Louizos , Max Welling

The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the…

机器学习 · 计算机科学 2017-08-29 Prasoon Goyal , Zhiting Hu , Xiaodan Liang , Chenyu Wang , Eric Xing

Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data distributions evolve over time. We show that under non-stationary targets, isotropic Gaussian…

机器学习 · 计算机科学 2026-03-20 Ali Saheb Pasand , Johan Obando-Ceron , Aaron Courville , Pouya Bashivan , Pablo Samuel Castro

Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the expressiveness of the…

机器学习 · 计算机科学 2018-06-12 Lars Mescheder , Sebastian Nowozin , Andreas Geiger

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

The representation of the approximate posterior is a critical aspect of effective variational autoencoders (VAEs). Poor choices for the approximate posterior have a detrimental impact on the generative performance of VAEs due to the…

机器学习 · 统计学 2020-06-09 Arash Vahdat , Evgeny Andriyash , William G. Macready

Deep Gaussian processes (DGPs) are multi-layer hierarchical generalisations of Gaussian processes (GPs) and are formally equivalent to neural networks with multiple, infinitely wide hidden layers. DGPs are probabilistic and non-parametric…

We propose a representation of Gaussian processes (GPs) based on powers of the integral operator defined by a kernel function, we call these stochastic processes integral Gaussian processes (IGPs). Sample paths from IGPs are functions…

机器学习 · 统计学 2019-03-08 Zilong Tan , Sayan Mukherjee

The variational autoencoder (VAE) is a generative model with continuous latent variables where a pair of probabilistic encoder (bottom-up) and decoder (top-down) is jointly learned by stochastic gradient variational Bayes. We first…

机器学习 · 统计学 2016-04-19 Suwon Suh , Seungjin Choi

Variational Autoencoders (VAEs) are powerful generative models for learning latent representations. Standard VAEs generate dispersed and unstructured latent spaces by utilizing all dimensions, which limits their interpretability, especially…

计算机视觉与模式识别 · 计算机科学 2025-05-21 Farshad Sangari Abiz , Reshad Hosseini , Babak N. Araabi

Recent advances have shown that GP priors, or their finite realisations, can be encoded using deep generative models such as variational autoencoders (VAEs). These learned generators can serve as drop-in replacements for the original priors…

Gaussian Processes (GPs) provide a flexible and statistically principled foundation for modelling spatiotemporal phenomena, but their $O(N^3)$ scaling makes them intractable for large datasets. Approximate methods such as variational…

机器学习 · 统计学 2026-04-01 Jhonathan Navott , Daniel Jenson , Seth Flaxman , Elizaveta Semenova

Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. However, recent studies demonstrate that,…

机器学习 · 计算机科学 2019-01-08 Xuezhe Ma , Chunting Zhou , Eduard Hovy