Robust Quantization: One Model to Rule Them All
This work addresses the need for flexible and efficient model deployment in resource-constrained environments, though it is incremental in improving quantization robustness.
The paper tackles the problem of neural network quantization's dependency on specific bit-widths and policies by proposing a robust quantization method that allows a single model to operate effectively across various quantization settings, achieving competitive accuracy on ImageNet models.
Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed. Robust quantization offers an alternative approach with improved tolerance to different classes of data-types and quantization policies. It opens up new exciting applications where the quantization process is not static and can vary to meet different circumstances and implementations. To address this issue, we propose a method that provides intrinsic robustness to the model against a broad range of quantization processes. Our method is motivated by theoretical arguments and enables us to store a single generic model capable of operating at various bit-widths and quantization policies. We validate our method's effectiveness on different ImageNet models.