energylossbeta: Energy Loss Calculation with Beta Scaling

In engression: Engression Modelling

Energy Loss Calculation with Beta Scaling

Description

This function calculates the energy loss for given tensors. The loss is calculated as the mean of the L2 norms between yt and mxt and between yt and mxpt, each raised to the power of beta, subtracted by half the mean of the L2 norm between mxt and mxpt, also raised to the power of beta.

Usage

energylossbeta(yt, mxt, mxpt, beta)

Arguments

yt	A tensor representing the target values.
mxt	A tensor representing the model's stochastic predictions.
mxpt	A tensor representing another draw of the model's stochastic predictions.
beta	A numeric value for scaling the energy loss.

Value

A scalar representing the calculated energy loss.

engression documentation built on April 16, 2026, 9:06 a.m.