LRS_NF
[AISTATS2020] The official repository of "Invertible Generative Modling using Linear Rational Splines (LRS)".
view repo
Normalizing flows attempt to model an arbitrary probability distribution through a set of invertible mappings. These transformations are required to achieve a tractable Jacobian determinant that can be used in high-dimensional scenarios. The first normalizing flow designs used coupling layer mappings built upon affine transformations. The significant advantage of such models is their easy-to-compute inverse. Nevertheless, making use of affine transformations may limit the expressiveness of such models. Recently, invertible piecewise polynomial functions as a replacement for affine transformations have attracted attention. However, these methods require solving a polynomial equation to calculate their inverse. In this paper, we explore using linear rational splines as a replacement for affine transformations used in coupling layers. Besides having a straightforward inverse, inference and generation have similar cost and architecture in this method. Moreover, simulation results demonstrate the competitiveness of this approach's performance compared to existing methods.
READ FULL TEXT
Good parametrisations of affine transformations are essential to
interpo...
read it
Most quantum compiler transformations and qubit allocation techniques to...
read it
In this paper, we present a new class of invertible transformations. We
...
read it
Normalizing flows have emerged as an important family of deep neural net...
read it
We exhibit an algorithm to compute the strongest polynomial (or algebrai...
read it
Normalizing flows are among the most popular paradigms in generative
mod...
read it
In this work, we propose Sum-Product-Transform Networks (SPTN), an exten...
read it
[AISTATS2020] The official repository of "Invertible Generative Modling using Linear Rational Splines (LRS)".
Comments
There are no comments yet.