What is the purpose of decreased FLOPs and parameter size if they are not for increased speed?

Question

CNN algorithms like DenseNet DenseNet stress parameter efficiency, which usually results in less FLOPs. However, what I am struggling to understand is why this is important. For DenseNet, in particular, it has low inference speed. Isn't the purpose of decreased parameter size/FLOPs to decrease the time for inference? Is there another real world reason, such as perhaps less energy used, for these optimizations?

Answer 1

There is a difference between overall inference time vs. per parameter/FLOPs training efficiency. Having lower parameter/FLOPs in training does not guarantee higher speed in inference. Because overall inference depends on the architecture and how predictions are computed.