zuko.flows.spline#

Spline flows.

Classes#

NSF

Creates a neural spline flow (NSF) with monotonic rational-quadratic spline transformations.

NCSF

Creates a neural circular spline flow (NCSF).

Descriptions#

class zuko.flows.spline.NSF(features, context=0, bins=8, **kwargs)#

Creates a neural spline flow (NSF) with monotonic rational-quadratic spline transformations.

By default, transformations are fully autoregressive. Coupling transformations can be obtained by setting passes=2.

Warning

Spline transformations are defined over the domain \([-5, 5]\). Any feature outside of this domain is not transformed. It is recommended to standardize features (zero mean, unit variance) before training.

See also

zuko.transforms.MonotonicRQSTransform

References

Neural Spline Flows (Durkan et al., 2019)
https://arxiv.org/abs/1906.04032
Parameters:

  • features (int) – The number of features.

  • context (int) – The number of context features.

  • bins (int) – The number of bins \(K\).

  • kwargs – Keyword arguments passed to zuko.flows.autoregressive.MAF.

class zuko.flows.spline.NCSF(features, context=0, bins=8, **kwargs)#

Creates a neural circular spline flow (NCSF).

Circular spline transformations are obtained by composing circular domain shifts with regular spline transformations. Features are assumed to lie in the half-open interval \([-\pi, \pi[\).

See also

zuko.transforms.CircularShiftTransform

References

Normalizing Flows on Tori and Spheres (Rezende et al., 2020)
https://arxiv.org/abs/2002.02428
Parameters:

  • features (int) – The number of features.

  • context (int) – The number of context features.

  • bins (int) – The number of bins \(K\).

  • kwargs – Keyword arguments passed to zuko.flows.autoregressive.MAF.