Post-training Neural Network (NN) model compression is an attractive approach for deploying large, memory-consuming models on devices with limited memory resources. In this study, we investigate the rate-distortion tradeoff for NN model compression. First, we suggest a Rotation-Invariant Quantization (RIQ) technique that utilizes a single parameter to quantize the entire NN model, yielding a different rate at each layer, i.e., mixed-precision quantization. Then, we prove that our rotation-invariant approach is optimal in terms of compression. We rigorously evaluate RIQ and demonstrate its capabilities on various models and tasks. For example, RIQ facilitates $\times 19.4$ and $\times 52.9$ compression ratios on pre-trained VGG dense and pruned models, respectively, with $<0.4\%$ accuracy degradation. Code: \url{https://github.com/ehaleva/RIQ}.

翻译：后训练神经网络模型压缩是一种在内存受限设备上部署大型、消耗内存模型的有效方法。本研究探讨了神经网络模型压缩中的率失真权衡。首先，我们提出了一种旋转不变量化技术，该技术利用单一参数对整个神经网络模型进行量化，从而在不同层产生不同的量化位宽，即混合精度量化。随后，我们证明了该旋转不变方法在压缩性能上具有最优性。我们对RIQ进行了严格评估，并在多种模型和任务上展示了其能力。例如，RIQ在预训练的VGG密集模型和剪枝模型上分别实现了$\times 19.4$和$\times 52.9$的压缩比，且准确率下降低于$0.4\%$。代码：\url{https://github.com/ehaleva/RIQ}。