Auto-Encoding Variational Bayes
The reparameterization trick turns a variational lower bound into a trainable autoencoder.
Kingma, Welling · ICLR 2014 · Foundations. Read the paper ↗
A free, interactive, animated visual explainer of Auto-Encoding Variational Bayes — every exhibit computed from the real formulas, with verbatim quotes from the source.
Questions
- What is Auto-Encoding Variational Bayes?
- The reparameterization trick turns a variational lower bound into a trainable autoencoder.
- Who published Auto-Encoding Variational Bayes, and where?
- Kingma, Welling — ICLR 2014 (arXiv:1312.6114).
- Where can I find a visual explainer of Auto-Encoding Variational Bayes?
- Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.
Related explainers
- Attention Is All You Need
- GPT-3: Language Models are Few-Shot Learners
- Mixtral of Experts
- Training Compute-Optimal Large Language Models
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- BERT: Pre-training of Deep Bidirectional Transformers
- Scaling Laws for Neural Language Models
- Adam: A Method for Stochastic Optimization