Robust Quantization: One Model to Rule Them All

TL;DR

This paper introduces a robust quantization method that creates a single neural network model capable of adapting to various bit-widths and quantization policies, enhancing flexibility and application scope.

Contribution

We propose a theoretically motivated approach that yields a single, versatile model robust to different quantization schemes, unlike traditional methods dependent on specific configurations.

Findings

Effective across multiple ImageNet models

Supports various bit-widths and policies

Improves model robustness to quantization variations

Abstract

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.