AdaQAT: Adaptive Bit-Width Quantization-Aware Training

arXiv:2404.16876v1 Announce Type: new
Abstract: Large-scale deep neural networks (DNNs) have achieved remarkable success in many application scenarios. However, high computational complexity and energy costs of modern DNNs make their deployment on edge devices challenging. Model quantization is a common approach to deal with deployment constraints, but searching for optimized bit-widths can be challenging. In this work, we present Adaptive Bit-Width Quantization Aware Training (AdaQAT), a learning-based method that automatically optimizes weight and activation signal bit-widths during training for more …

abstract application arxiv complexity computational constraints costs cs.ai cs.lg deal deployment devices edge edge devices energy energy costs however modern networks neural networks quantization scale searching success training type