An Introduction to Variational Autoencoders

DOI10.1561/2200000056zbMath1431.68002arXiv1906.02691OpenAlexW2948978827WikidataQ126647299 ScholiaQ126647299MaRDI QIDQ5213204

Diederik P. Kingma, Max Welling

Publication date: 31 January 2020

Published in: Foundations and Trends® in Machine Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1906.02691

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Learning and adaptive systems in artificial intelligence (68T05) Research exposition (monographs, survey articles) pertaining to computer science (68-02)

Related Items (77)

Solving inverse problems using conditional invertible neural networks ⋮ Machine learning techniques to construct patched analog ensembles for data assimilation ⋮ Inverse design of locally resonant metabarrier by deep learning with a rule-based topology dataset ⋮ Transform a simple sketch to a Chinese painting by a multiscale deep neural network ⋮ Geometry and generalization: eigenvalues as predictors of where a network will fail to generalize ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ A heteroencoder architecture for prediction of failure locations in porous metals using variational inference ⋮ Autoencoders reloaded ⋮ Encoded value-at-risk: a machine learning approach for portfolio risk measurement ⋮ Learning nonlinear state-space models using autoencoders ⋮ Quantum generative adversarial network for generating discrete distribution ⋮ Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior ⋮ A hybrid objective function for robustness of artificial neural networks -- estimation of parameters in a mechanical system ⋮ A survey of unsupervised learning methods for high-dimensional uncertainty quantification in black-box-type problems ⋮ Sampling the Riemann-theta Boltzmann machine ⋮ Conditional quantum circuit Born machine based on a hybrid quantum-classical framework ⋮ Generative modeling via tensor train sketching ⋮ Radon-Sobolev variational auto-encoders ⋮ A semi-supervised zero-shot image classification method based on soft-target ⋮ On the capacity of deep generative networks for approximating distributions ⋮ Conditional variational autoencoder with Gaussian process regression recognition for parametric models ⋮ An introduction to deep generative modeling ⋮ Deep dynamic modeling with just two time points: Can we still allow for individual trajectories? ⋮ Robust node embedding against graph structural perturbations ⋮ Prior density learning in variational Bayesian phylogenetic parameters inference ⋮ Reservoir computing with error correction: long-term behaviors of stochastic dynamical systems ⋮ Fully probabilistic deep models for forward and inverse problems in parametric PDEs ⋮ Uncertainty quantification in scientific machine learning: methods, metrics, and comparisons ⋮ Scaling Up Bayesian Uncertainty Quantification for Inverse Problems Using Deep Neural Networks ⋮ Modern AI \textit{versus} century-old mathematical models: how far can we go with generative adversarial networks to reproduce stochastic processes? ⋮ Manifold learning for coherent design interpolation based on geometrical and topological descriptors ⋮ CSPM: discovering compressing stars in attributed graphs ⋮ Unnamed Item ⋮ Generative methods for sampling transition paths in molecular dynamics ⋮ Isotonic recalibration under a low signal-to-noise ratio ⋮ Neural nets with a Newton conjugate gradient method on multiple GPUs ⋮ Tutorial on Amortized Optimization ⋮ An introduction to machine learning: a perspective from statistical physics ⋮ Poisson Reweighted Laplacian Uncertainty Sampling for Graph-Based Active Learning ⋮ ToFU: topology functional units for deep learning ⋮ Regularising inverse problems with generative machine learning models ⋮ WSN optimization for sampling-based signal estimation using semi-binarized variational autoencoder ⋮ Separability, contextuality, and the quantum frame problem ⋮ Achieving deep clustering through the use of variational autoencoders and similarity-based loss ⋮ A machine learning framework for geodesics under spherical Wasserstein-Fisher-Rao metric and its application for weighted sample generation ⋮ Broadband Acoustic Metamaterial Design via Machine Learning ⋮ Densities of almost surely terminating probabilistic programs are differentiable almost everywhere ⋮ \(\beta\)-Variational autoencoder as an entanglement classifier ⋮ Counterfactual state explanations for reinforcement learning agents via generative deep learning ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Deep learning of thermodynamics-aware reduced-order models from data ⋮ Resolving learning rates adaptively by locating stochastic non-negative associated gradient projection points using line searches ⋮ A tutorial review of mathematical techniques for quantifying tumor heterogeneity ⋮ A gentle introduction to deep learning for graphs ⋮ Fusing sufficient dimension reduction with neural networks ⋮ Spatial voting models in circular spaces: a case study of the U.S. House of Representatives ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Stabilizing Invertible Neural Networks Using Mixture Models ⋮ A tale of three probabilistic families: Discriminative, descriptive, and generative models ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Recursive tree grammar autoencoders ⋮ Dynamical Variational Autoencoders: A Comprehensive Review ⋮ \(\pi\) VAE: a stochastic process prior for Bayesian deep learning with MCMC

This page was built for publication: An Introduction to Variational Autoencoders