Differentiable Search for Finding Optimal Quantization Strategy

arXiv:2404.08010v1 Announce Type: new
Abstract: To accelerate and compress deep neural networks (DNNs), many network quantization algorithms have been proposed. Although the quantization strategy of any algorithm from the state-of-the-arts may outperform others in some network architectures, it is hard to prove the strategy is always better than others, and even cannot judge that the strategy is always the best choice for all layers in a network. In other words, existing quantization algorithms are suboptimal as they ignore the different …

abstract algorithm algorithms architectures arts arxiv cs.lg differentiable eess.iv judge network networks neural networks prove quantization search state strategy type