Neural network quantization methods often involve simulating the quantization process during training. This makes the trained model highly dependent on the precise way quantization is performed. Since low-precision accelerators differ in their quantization policies and their supported mix of data-types, a model trained for one accelerator may not be suitable for another. To address this issue, we propose KURE, a method that provides intrinsic robustness to the model against a broad range of quantization implementations. We show that KURE yields a generic model that may be deployed on numerous inference accelerators without a significant loss in accuracy.
Speakers: Moran Shkolnik, Brian Chmiel, Ron Banner, Gil Shomron, Yury Nahshan, Alex Bronstein, Uri Weiser