Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models

🤖 Plain-English Summary

Deep generative models are a class of techniques that train deep neural networks to model the distribution of training samples. In particular, this compendium covers energy-based models, variational autoencoders, generative adversarial networks, autoregressive models, normalizing flows, in addition to numerous hybrid approaches.

🔑 Key Findings

• Research has fragmented into various interconnected approaches, each of which make trade-offs including run-time, diversity, and architectural restrictions.
• In particular, this compendium covers energy-based models, variational autoencoders, generative adversarial networks, autoregressive models, normalizing flows, in addition to numerous hybrid approaches.
• These techniques are compared and contrasted, explaining the premises behind each and how they are interrelated, while reviewing current advanced advances and implementations.

🔗 Related Resources