Auto-Encoding Variational Bayes
Explore this paper's citation graph
Summary
A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
- Type
- article
- Published
- 2013-12-20
- Cited by
- 17,260
- References
- 26
- Access
- Open access
- OpenAlex
- https://openalex.org/W1959608418
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:216078090
Keywords
Inference, Estimator, Upper and lower bounds, Latent variable, Differentiable function
References
- Efficient Learning of Deep Boltzmann Machines
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- To Center or Not to Center: That Is Not the Question—An Ancillarity–Sufficiency Interweaving Strategy (ASIS) for Boosting MCMC Efficiency
- The "wake-sleep" algorithm for unsupervised neural networks.
- A General Framework for the Parametrization of Hierarchical Models
- Auto-association by multilayer perceptrons and singular value decomposition
- Fixed-Form Variational Posterior Approximation through Stochastic Linear Regression
- Hybrid Monte Carlo
- Sample-based non-uniform random variate generation
- Deep AutoRegressive Networks
- EM Algorithms for PCA and SPCA
- Practical Variational Inference for Neural Networks
- Variational Bayesian Inference with Stochastic Search
- Deep Generative Stochastic Networks Trainable by Backprop
- An Application of the Principle of Maximum Information Preservation to Linear Systems
- Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
- Representation Learning: A Review and New Perspectives
- Stochastic variational inference
- Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition
- Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
Cited by
- Conditional Variational Autoencoder for Prediction and Feature Recovery Applied to Intrusion Detection in IoT
- Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
- A Learning Framework for Winner-Take-All Networks with Stochastic Synapses
- Semisupervised Text Classification by Variational Autoencoder
- Deep Directed Generative Autoencoders
- Nested Variational Compression in Deep Gaussian Processes
- Unsupervised Visual Representation Learning by Context Prediction
- A Recurrent Latent Variable Model for Sequential Data
- Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
- Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
- The Population Posterior and Bayesian Inference on Streams
- Deep Gaussian processes and variational propagation of uncertainty
- Techniques for Learning Binary Stochastic Feedforward Neural Networks
- Local Expectation Gradients for Doubly Stochastic Variational Inference
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Towards Biologically Plausible Deep Learning
- Learning Deep Generative Models with Doubly Stochastic MCMC
- Automatic Relevance Determination For Deep Generative Models
- Training opposing directed models using geometric mean matching
- Leave Pima Indians alone: binary regression as a benchmark for Bayesian computation