Free Information Center
Neural spline flow (NSF) is a class of normalizing flow models that use spline-based transformations to enable flexible, invertible mappings for density estimation and generative modeling. By leveraging piecewise spline functions, NSF can represent complex distributions with improved accuracy and stability compared to traditional flow architectures.
A flow-based generative model is a type of machine learning model that generates data by learning invertible mappings between complex data distributions and simple latent variables. These models enable exact likelihood computation and efficient sampling, distinguishing them from other generative approaches.
RealNVP (real-valued non-volume preserving) is a type of generative model in machine learning that utilizes invertible neural networks for density estimation and sampling. It enables exact log-likelihood computation and efficient generation of complex data distributions, particularly in image modeling.
Masked autoregressive flow (MAF) is a type of normalizing flow used in machine learning for density estimation and generative modeling. It employs autoregressive models combined with masking techniques to create flexible, invertible transformations that allow efficient sampling and likelihood evaluation.