cram_expected_loss: Cram ML Expected Loss Estimate

In cramR: Cram Method for Efficient Simultaneous Learning and Evaluation

Cram ML Expected Loss Estimate

Description

This function computes the Cram ML expected loss estimator based on the given loss matrix and batch indices.

Usage

cram_expected_loss(loss, batch_indices)

Arguments

loss	A matrix of loss values with N rows (data points) and K+1 columns (batches). We assume that the first column of the loss matrix contains only zeros. The following nb_batch columns contain the losses of each trained model for each individual.
batch_indices	A list where each element is a vector of indices corresponding to a batch.

Value

The Cram ML expected loss estimate

cramR documentation built on Aug. 25, 2025, 1:12 a.m.