no code implementations • 16 Sep 2021 • Mark Buckler, Neil Adit, Yuwei Hu, Zhiru Zhang, Adrian Sampson
Our key insights are that 1) pointwise convolutions commute with frequency transformation and thus can be computed in the frequency domain without modification, 2) each channel within a given layer has a different level of sensitivity to frequency domain pruning, and 3) each channel's sensitivity to frequency pruning is approximately monotonic with respect to frequency.