Table 2.

Summary of notations.

Notation	Description
	Final predicted output for the ith input sample
	The ith input data sample
	Predicted class label by the nth model or client for input
	Summation overall N models or clients
	Averaging factor to compute the mean prediction from all contributors
	Total number of models or clients
	Statistical mode function that returns the most frequent class label
	Total loss function with parameters
	Total number of data samples
	Loss between ground truth and predicted output
	Summation overall n training samples
	Summation over all K model components
	Regularization term for the kth model component
	Model parameters of the kth component
	Overall set of model parameters
	Bias or constant term related to iteration T
	Regularization coefficient
	Total number of training iterations or time steps
	Model weight parameter at step j
	Sum of squared weights
	L2 regularization term
	Output of the kth model when applied to input
	Total number of models contributing to the aggregation
	Summation over all K models
	An estimated value at index k
	Summation from j = 0 to j = n, so summing up n + 1 terms
	Classifier
	Weight assigned to jth classifier