AI RESEARCH

ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNs

arXiv CS.LG

ArXi:2410.24214v3 Announce Type: replace Mixed precision quantization has become an important technique for optimizing the execution of deep neural networks (DNNs). Certified robustness, which provides provable guarantees about a model's ability to withstand different adversarial perturbations, has rarely been addressed in quantization due to the unacceptably high cost of certifying robustness. This paper