hypertools.reduce.autoencoders.VariationalAutoencoder

class hypertools.reduce.autoencoders.VariationalAutoencoder(n_components=2, kl_weight=1.0, hidden_dims=None, epochs=100, batch_size=64, lr=0.001, device='auto', random_state=None, verbose=False)

A variational autoencoder (VAE) reducer: a probabilistic encoder (mean + log-variance heads) trained with a KL-divergence term toward a standard normal prior, via the reparameterization trick. transform/fit_transform return the latent MEANS (not stochastic samples), giving a smooth, reproducible, generative latent space.

Parameters:

n_componentsint

Latent dimensionality (default: 2).

kl_weightfloat

Weight of the KL-divergence term, added to the MSE reconstruction loss (default: 1.0).

hidden_dimsNone, int, or sequence of int

Hidden layer widths of the shared encoder body / decoder, outermost (closest to the input) first. None (default) computes 2 geometrically-spaced widths.

epochs, batch_size, lr, device, random_state, verbose

See Autoencoder.

Attributes:

net_torch.nn.Module or None

The fitted network.

Methods

fit(X[, y])	Fit the autoencoder on X (see fit_transform); returns self.
fit_transform(X[, y])	Standardize X, train a fresh network on it, and return the fitted latent codes.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
inverse_transform(Z)	Decode latent codes Z back to (standardization-undone) feature space.
set_inverse_transform_request(*[, Z])	Configure whether metadata should be requested to be passed to the inverse_transform method.
set_params(**params)	Set the parameters of this estimator.
transform(X)	Apply the already-fitted network to (new) X, without refitting.

__init__(n_components=2, kl_weight=1.0, hidden_dims=None, epochs=100, batch_size=64, lr=0.001, device='auto', random_state=None, verbose=False)

Methods

__init__([n_components, kl_weight, ...])
fit(X[, y])	Fit the autoencoder on X (see fit_transform); returns self.
fit_transform(X[, y])	Standardize X, train a fresh network on it, and return the fitted latent codes.
get_metadata_routing()	Get metadata routing of this object.
get_params([deep])	Get parameters for this estimator.
inverse_transform(Z)	Decode latent codes Z back to (standardization-undone) feature space.
set_inverse_transform_request(*[, Z])	Configure whether metadata should be requested to be passed to the inverse_transform method.
set_params(**params)	Set the parameters of this estimator.
transform(X)	Apply the already-fitted network to (new) X, without refitting.

Attributes

is_fitted

Whether fit/fit_transform has already been run.