Fig. 1

Potential sub-matrix growth shown for up to 14 batches. The y-axis is in a logarithmic scale. The orange curve shows the maximum expected growth using default HarmonizR according to the sum of binomial coefficients \(t_{n,\text{max}} = \text{min} \left( { F}, \sum _{k=2}^{n} {n\atopwithdelims ()k} \right)\) with the maximum number of features F and total number of batches n [12]. The blue and red curves show the growth when using the blocking approach presented in this paper with the parameters 2 and 4 respectively