FactorVAEOptions<T>

Options & Configuration · AiDotNet.Models.Options

Configuration options for the FactorVAE model.

Inheritance: ModelOptions → FactorVAEOptions<T>

For Beginners

FactorVAE learns a compressed representation of market data. You can decide how many hidden factors to discover and how strongly to enforce disentanglement.

How It Works

FactorVAE is a variational autoencoder tailored to learning disentangled financial factors. These options control the latent space size, factor count, and regularization strengths.

Constructors

Constructor Summary
FactorVAEOptions()

Properties

Property Summary
bool UseAMSGrad { get; set; } Gets or sets whether the model’s default Adam optimizer uses the AMSGrad second-moment maximum.
double Beta { get; set; } Gets or sets the beta coefficient for the VAE KL term.
double DropoutRate { get; set; } Gets or sets the dropout rate used for regularization.
double Gamma { get; set; } Gets or sets the gamma coefficient for the factor disentanglement penalty.
double KlWeight { get; set; } Gets or sets the weight on the prior-posterior KL divergence.
int HiddenDimension { get; set; } Gets or sets the width of hidden layers.
int LatentDimension { get; set; } Gets or sets the dimension of the latent space.
int NumAssets { get; set; } Gets or sets the number of assets covered by the model.
int NumFactors { get; set; } Gets or sets the number of latent factors to learn.
int NumFeatures { get; set; } Gets or sets the number of input features.
int PredictionHorizon { get; set; } Gets or sets the prediction horizon.
int SequenceLength { get; set; } Gets or sets the input sequence length.

Methods

Method Summary
void Validate() Validates the options and throws if any value is invalid.