If you want to know how people did matching pursuit in the 40s to compute stresses in a network of springs (and implicitly compute the product of the inverse of a "huge" 13x13 matrix with a vector), here is a slight update on an old post of mine:

"Matching Pursuit Before Computer Science" https://laurentjacques.gitlab.io/post/matching-pursuit-before-computer-science/

(a post recently moved on my homepage from WordPress) #Sparsity #SignalProcessing #GreedyMethods