e287f0b2e730059c55d97fa92649f4f2-AuthorFeedback.pdf

The execution time for inference is not provided in the paper. We will state this in the next revision. The advantage of the proposed algorithm is clear for the discrete tasks but not for continuous tasks. The results are competitive with SOTA so we have elected to include them for completeness. I think the authors used seven datasets out of the eight datasets described in the paper [7].