Metrics that allow the parametric forecast of parameters of uni- and multivariate distributions.


BetaDistributionLoss([name, quantiles, ...])

Beta distribution loss for unit interval data.

ImplicitQuantileNetwork(input_size, hidden_size)

Initializes internal Module state, shared by both nn.Module and ScriptModule.


Implicit Quantile Network Distribution Loss.

LogNormalDistributionLoss([name, quantiles, ...])

Log-normal loss.

MQF2DistributionLoss(prediction_length[, ...])

Multivariate quantile loss based on the article Multivariate Quantile Function Forecaster.

MultivariateNormalDistributionLoss([name, ...])

Multivariate low-rank normal distribution loss.

NegativeBinomialDistributionLoss([name, ...])

Negative binomial loss, e.g.

NormalDistributionLoss([name, quantiles, ...])

Normal distribution loss.