Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization
By: Haidong Kang , Lianbo Ma , Guo Yu and more
Potential Business Impact:
Makes AI smarter by using less computer power.
Mixed precision quantization (MPQ) is an effective quantization approach to achieve accuracy-complexity trade-off of neural network, through assigning different bit-widths to network activations and weights in each layer. The typical way of existing MPQ methods is to optimize quantization policies (i.e., bit-width allocation) in a gradient descent manner, termed as Differentiable (DMPQ). At the end of the search, the bit-width associated to the quantization parameters which has the largest value will be selected to form the final mixed precision quantization policy, with the implicit assumption that the values of quantization parameters reflect the operation contribution to the accuracy improvement. While much has been discussed about the MPQ improvement, the bit-width selection process has received little attention. We study this problem and argue that the magnitude of quantization parameters does not necessarily reflect the actual contribution of the bit-width to the task performance. Then, we propose a Shapley-based MPQ (SMPQ) method, which measures the bit-width operation direct contribution on the MPQ task. To reduce computation cost, a Monte Carlo sampling-based approximation strategy is proposed for Shapley computation. Extensive experiments on mainstream benchmarks demonstrate that our SMPQ consistently achieves state-of-the-art performance than gradient-based competitors.
Similar Papers
InfoQ: Mixed-Precision Quantization via Global Information Flow
Machine Learning (CS)
Makes AI smarter on small devices.
Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning
CV and Pattern Recognition
Makes AI smarter with less computer power.
Mixed-Precision Quantization for Language Models: Techniques and Prospects
Machine Learning (CS)
Makes smart computer programs smaller and faster.