zuko.flows.neural#

Neural flows and transformations.

Classes#

MNN

Creates a monotonic neural network (MNN).

UMNN

Creates an unconstrained monotonic neural network (UMNN).

NAF

Creates a neural autoregressive flow (NAF).

UNAF

Creates an unconstrained neural autoregressive flow (UNAF).

Descriptions#

class zuko.flows.neural.MNN(signal=16, **kwargs)#

Creates a monotonic neural network (MNN).

The monotonic neural network is parametrized by its internal positive weights, which are independent of the features and context. To modulate its behavior, it receives as input a signal vector that can depend on the features and context.

See also

zuko.transforms.MonotonicTransform

References

Neural Autoregressive Flows (Huang et al., 2018)
https://arxiv.org/abs/1804.00779
Parameters:

  • signal (int) – The number of signal features of the monotonic network.

  • kwargs – Keyword arguments passed to zuko.nn.MonotonicMLP.

class zuko.flows.neural.UMNN(signal=16, **kwargs)#

Creates an unconstrained monotonic neural network (UMNN).

The integrand neural network is parametrized by its internal weights, which are independent of the features and context. To modulate its behavior, it receives as input a signal vector that can depend on the features and context.

See also

zuko.transforms.UnconstrainedMonotonicTransform

References

Unconstrained Monotonic Neural Networks (Wehenkel et al., 2019)
https://arxiv.org/abs/1908.05164
Parameters:

  • signal (int) – The number of signal features of the integrand network.

  • kwargs – Keyword arguments passed to zuko.nn.MLP.

class zuko.flows.neural.NAF(features, context=0, transforms=3, randperm=False, signal=16, network={}, **kwargs)#

Creates a neural autoregressive flow (NAF).

Warning

Invertibility is only guaranteed for features within the interval \([-10, 10]\). It is recommended to standardize features (zero mean, unit variance) before training.

References

Neural Autoregressive Flows (Huang et al., 2018)
https://arxiv.org/abs/1804.00779
Parameters:

  • features (int) – The number of features.

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

  • transforms (int) – The number of autoregressive transformations.

  • randperm (bool) – Whether features are randomly permuted between transformations or not. If False, features are in ascending (descending) order for even (odd) transformations.

  • signal (int) – The number of signal features of the monotonic network.

  • network (Dict[str, Any]) – Keyword arguments passed to MNN.

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

class zuko.flows.neural.UNAF(features, context=0, transforms=3, randperm=False, signal=16, network={}, **kwargs)#

Creates an unconstrained neural autoregressive flow (UNAF).

Warning

Invertibility is only guaranteed for features within the interval \([-10, 10]\). It is recommended to standardize features (zero mean, unit variance) before training.

References

Unconstrained Monotonic Neural Networks (Wehenkel et al., 2019)
https://arxiv.org/abs/1908.05164
Parameters:

  • features (int) – The number of features.

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

  • transforms (int) – The number of autoregressive transformations.

  • randperm (bool) – Whether features are randomly permuted between transformations or not. If False, features are in ascending (descending) order for even (odd) transformations.

  • signal (int) – The number of signal features of the monotonic network.

  • network (Dict[str, Any]) – Keyword arguments passed to UMNN.

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