The metric computation for MP-SA using the estimated channel sparsity and the initial metric computation for MA-SA have the same complexity.
In order to compute the metric for a given path, the MP-SA method detects the channel sparsity first and computes the metric using the estimated channel sparsity, while the MA-SA method computes the initial metric for d(0)= [ 0,…,0] and updates the metric with the sparsity detection.
We used values along the PCA axes in order to ensure that calculations of similarity between landscapes were not biased toward certain aspects of landscapes that had been computed redundantly in the initial metric set.
CIEEM members who have practical experience of using the current metric have commented that it is difficult to use.
We assessed the classification performance using the AUC metric.
Imputation quality was assessed using the R metric.
We also quantified heterogeneity using the I metric (94).
Average linkage hierarchical clustering was performed using the Euclidian metric.
We also quantified heterogeneity using the I2 metric.
The procedures using the metric learning algorithm are summarized in Figure 2. Metric learning is performed in the learning stage.
