An Introduction to Variational Autoencoders

2019/06/30 by Diederik P. Kingma, Max Welling · 17 citations
Computer Science · Mathematics · #cs.LG #stat.ML

paper · pdf · doi:10.1561/2200000056

published as Foundations and Trends in Machine Learning: Vol. 12 (2019): No. 4, pp 307-392

arxiv created 2019/12/11 · arxiv updated 2019/12/12

Abstract

Variational autoencoders provide a principled framework for learning deep latent-variable models and corresponding inference models. In this work, we provide an introduction to variational autoencoders and some important extensions.

Cited by

• Image Generation with a Sphere Encoder
• A Unifying Framework for Unsupervised Concept Extraction
• Synthetic Power Flow Data Generation Using Physics-Informed Denoising Diffusion Probabilistic Models
• Likelihood-Free Variational Autoencoders
• Semi-Blind Strategies for MMSE Channel Estimation Utilizing Generative Priors
• Enhancing Variational Autoencoders with Smooth Robust Latent Encoding
• Intrinsic-Hybrid Latent Diffusion Models for Generative Modeling on Unknown Manifolds
• Latent Video Dataset Distillation
• Towards responsible AI for education: Hybrid human-AI to confront the Elephant in the room
• RadioDiff-k²: Helmholtz Equation Informed Generative Diffusion Model for Multi-Path Aware Radio Map Construction
• Shifts in Doctors' Eye Movements Between Real and AI-Generated Medical Images
• Impact of Latent Space Dimension on IoT Botnet Detection Performance: VAE-Encoder Versus ViT-Encoder
• Support is All You Need for Certified VAE Training
• A Diffusion-Based Framework for Terrain-Aware Remote Sensing Image Reconstruction
• Deep Generalised Mixed Models: a Novel Neural Network Structure for Analysing Hierarchical Data
• VAE-based Feature Disentanglement for Data Augmentation and Compression in Generalized GNSS Interference Classification
• GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

Related

• Latent Variable Modelling Using Variational Autoencoders: A survey
• Three Variations on Variational Autoencoders
• Inducing Interpretable Representations with Variational Autoencoders
• An Introduction to Discrete Variational Autoencoders
• Training Latent Variable Models with Auto-encoding Variational Bayes: A Tutorial