Timezone: »

Robust Quantization: One Model to Rule Them All
moran shkolnik · Brian Chmiel · Ron Banner · Gil Shomron · Yury Nahshan · Alex Bronstein · Uri Weiser

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #847

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. A reference implementation accompanies the paper.

Author Information

moran shkolnik (Technion- Israel Institute of Technology)
Brian Chmiel (Intel)
Ron Banner (Intel - Artificial Intelligence Products Group (AIPG))
Gil Shomron (Technion - Israel Institute of Technology)
Yury Nahshan (Intel - Artificial Intelligence Products Group (AIPG))
Alex Bronstein (Technion)
Uri Weiser (Technion - Israel Institute of Technology)

More from the Same Authors