# A Data-Free Analytical Quantization Scheme for Deep Learning Models

arXiv: https://arxiv.org/abs/2412.07391 · HTML: https://mlsanity.com/paper/2412.07391/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Improving Neural Network Quantization without Retraining using Outlier Channel Splitting](https://mlsanity.com/paper/1901.09504/) (2019)
- [Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks](https://mlsanity.com/paper/1909.13144/) (2019)
- [FP8 Quantization: The Power of the Exponent](https://mlsanity.com/paper/2208.09225/) (2022)
- [Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation](https://mlsanity.com/paper/2111.14826/) (2021)
- [Intriguing Properties of Quantization at Scale](https://mlsanity.com/paper/2305.19268/) (2023)
- [Differentiable Joint Pruning and Quantization for Hardware Efficiency](https://mlsanity.com/paper/2007.10463/) (2020)
- [Structural Pruning via Latency-Saliency Knapsack](https://mlsanity.com/paper/2210.06659/) (2022)
- [OMPQ: Orthogonal Mixed Precision Quantization](https://mlsanity.com/paper/2109.07865/) (2021)
- [Adaptive Data-Free Quantization](https://mlsanity.com/paper/2303.06869/) (2023)
- [Data-Efficient Structured Pruning via Submodular Optimization](https://mlsanity.com/paper/2203.04940/) (2022)
- [The High-Dimensional Geometry of Binary Neural Networks](https://mlsanity.com/paper/1705.07199/) (2017)
- [Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions](https://mlsanity.com/paper/2209.08554/) (2022)
- [PDP: Parameter-free Differentiable Pruning is All You Need](https://mlsanity.com/paper/2305.11203/) (2023)
- [Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection](https://mlsanity.com/paper/2402.10062/) (2024)
- [Towards Feature Distribution Alignment and Diversity Enhancement for Data-Free Quantization](https://mlsanity.com/paper/2205.00179/) (2022)

## Abstract (arXiv)

Despite the success of CNN models on a variety of Image classification and segmentation tasks, their extensive computational and storage demands pose considerable challenges for real-world deployment on resource-constrained devices. Quantization is one technique that aims to alleviate these large storage requirements and speed up the inference process by reducing the precision of model parameters to lower-bit representations. In this paper, we introduce a novel post-training quantization method for model weights. Our method finds optimal clipping thresholds and scaling factors along with mathematical guarantees that our method minimizes quantization noise. Empirical results on real-world datasets demonstrate that our quantization scheme significantly reduces model size and computational requirements while preserving model accuracy.