Auto-Encoding Variational Bayes
Diederik P. Kingma, Max Welling · UvA-DARE (University of Amsterdam) · 2013
How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions are two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods. Second, we show that for i.i.d. datasets with continuous latent variables per datapoint, posterior inference can be made especially efficient by fitting an approximate inference model (also called a recognition model) to the intractable posterior using the proposed lower bound estimator. Theoretical advantages are reflected in experimental results.
Cited by 14,201 works. doi:10.48550/arxiv.1312.6114
Authors
References
- Representation Learning: A Review and New Perspectives
- Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion
- Hybrid Monte Carlo
- Fast Inference in Sparse Coding Algorithms with Applications to Object Recognition
- EM Algorithms for PCA and SPCA
- Deep AutoRegressive Networks
- An Application of the Principle of Maximum Information Preservation to Linear Systems
- Stochastic variational inference
- Efficient Learning of Deep Boltzmann Machines
- Variational Bayesian Inference with Stochastic Search