# Q-Rater: Non-Convex Optimization for Post-Training Uniform Quantization

arXiv: https://arxiv.org/abs/2105.01868 · HTML: https://mlsanity.com/paper/2105.01868/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 35 references that are in the map.
- First posted on arXiv 5 May 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations](https://mlsanity.com/paper/1609.07061/) (2016)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [The Loss Surfaces of Multilayer Networks](https://mlsanity.com/paper/1412.0233/) (2014)
- [Dynamic Network Surgery for Efficient DNNs](https://mlsanity.com/paper/1608.04493/) (2016)
- [Trained Ternary Quantization](https://mlsanity.com/paper/1612.01064/) (2016)
- [Qualitatively characterizing neural network optimization problems](https://mlsanity.com/paper/1412.6544/) (2014)
- [Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss](https://mlsanity.com/paper/1808.05779/) (2018)
- [Improving Neural Network Quantization without Retraining using Outlier Channel Splitting](https://mlsanity.com/paper/1901.09504/) (2019)
- [Fixed Point Quantization of Deep Convolutional Networks](https://mlsanity.com/paper/1511.06393/) (2015)
- [Loss Aware Post-training Quantization](https://mlsanity.com/paper/1911.07190/) (2019)
- [And the Bit Goes Down: Revisiting the Quantization of Neural Networks](https://mlsanity.com/paper/1907.05686/) (2019)
- [Towards the Limit of Network Quantization](https://mlsanity.com/paper/1612.01543/) (2016)
- [Resiliency of Deep Neural Networks under Quantization](https://mlsanity.com/paper/1511.06488/) (2015)
- [Fighting Quantization Bias With Bias](https://mlsanity.com/paper/1906.03193/) (2019)
- [Network Sketching: Exploiting Binary Structure in Deep CNNs](https://mlsanity.com/paper/1706.02021/) (2017)
- [Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks](https://mlsanity.com/paper/1706.07145/) (2017)
- [Fixed-Point Performance Analysis of Recurrent Neural Networks](https://mlsanity.com/paper/1512.01322/) (2015)
- [On the Compression of Recurrent Neural Networks with an Application to LVCSR acoustic modeling for Embedded Speech Recognition](https://mlsanity.com/paper/1603.08042/) (2016)
- [FleXOR: Trainable Fractional Quantization](https://mlsanity.com/paper/2009.04126/) (2020)

## Abstract (arXiv)

Various post-training uniform quantization methods have usually been studied based on convex optimization. As a result, most previous ones rely on the quantization error minimization and/or quadratic approximations. Such approaches are computationally efficient and reasonable when a large number of quantization bits are employed. When the number of quantization bits is relatively low, however, non-convex optimization is unavoidable to improve model accuracy. In this paper, we propose a new post-training uniform quantization technique considering non-convexity. We empirically show that hyper-parameters for clipping and rounding of weights and activations can be explored by monitoring task loss. Then, an optimally searched set of hyper-parameters is frozen to proceed to the next layer such that an incremental non-convex optimization is enabled for post-training quantization. Throughout extensive experimental results using various models, our proposed technique presents higher model accuracy, especially for a low-bit quantization.