One-Shot Model for Mixed-Precision Quantization
Ivan Koryakovskiy, Alexandra Yakovleva, Valentin Buchnev, Temur Isaev, Gleb Odinokikh
Abstract
Neural network quantization is a popular approach for model compression. Modern hardware supports quantization in mixed-precision mode, which allows for greater compression rates but adds the challenging task of searching for the optimal bit width. The majority of existing searchers find a single mixed-precision architecture. To select an architecture that is suitable in terms of performance and resource consumption, one has to restart searching multiple times. We focus on a specific class of methods that find tensor bit width using gradient-based optimization. First, we theoretically derive several methods that were empirically proposed earlier. Second, we present a novel One-Shot method that finds a diverse set of Pareto-front architectures in <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$O(1)$</tex> time. For large models, the proposed method is 5 times more efficient than existing methods. We verify the method on two classification and super-resolution models and show above 0.93 correlation score between the predicted and actual model performance. The Paretofront architecture selection is straightforward and takes only 20 to 40 supernet evaluations, which is the new state-of-the-art result to the best of our knowledge.