# Retraining-free Model Quantization via One-Shot Weight-Coupling Learning

arXiv: https://arxiv.org/abs/2401.01543 · HTML: https://mlsanity.com/paper/2401.01543/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 70 references that are in the map.
- First posted on arXiv 3 Jan 2024.

## Builds on (most cited first, 30 of 58)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [HAQ: Hardware-Aware Automated Quantization with Mixed Precision](https://mlsanity.com/paper/1811.08886/) (2018)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision](https://mlsanity.com/paper/1905.03696/) (2019)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks](https://mlsanity.com/paper/1908.05033/) (2019)
- [BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models](https://mlsanity.com/paper/2003.11142/) (2020)

## Built on by (most cited first, 13 of 13)

- [SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration](https://mlsanity.com/paper/2506.12723/) (2025)
- [Low-bit Model Quantization for Deep Neural Networks: A Survey](https://mlsanity.com/paper/2505.05530/) (2025)
- [TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models](https://mlsanity.com/paper/2404.09532/) (2024)
- [PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference](https://mlsanity.com/paper/2407.05010/) (2024)
- [SizeGS: Size-aware Compression of 3D Gaussian Splatting via Mixed Integer Programming](https://mlsanity.com/paper/2412.05808/) (2024)
- [One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments](https://mlsanity.com/paper/2405.20202/) (2024)
- [Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling](https://mlsanity.com/paper/2510.20673/) (2025)
- [GAQAT: gradient-adaptive quantization-aware training for domain generalization](https://mlsanity.com/paper/2412.05551/) (2024)
- [Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective](https://mlsanity.com/paper/2509.00859/) (2025)
- [Precision Neural Network Quantization via Learnable Adaptive Modules](https://mlsanity.com/paper/2504.17263/) (2025)
- [RTF-Q: Efficient Unsupervised Domain Adaptation with Retraining-free Quantization](https://mlsanity.com/paper/2408.05752/) (2024)
- [CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration](https://mlsanity.com/paper/2510.03038/) (2025)
- [MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searching](https://mlsanity.com/paper/2604.26799/) (2026)

## Abstract (arXiv)

Quantization is of significance for compressing the over-parameterized deep neural models and deploying them on resource-limited devices. Fixed-precision quantization suffers from performance drop due to the limited numerical representation ability. Conversely, mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers. MPQ is typically organized into a searching-retraining two-stage process. In this paper, we devise a one-shot training-searching paradigm for mixed-precision model compression. Specifically, in the first stage, all potential bit-width configurations are coupled and thus optimized simultaneously within a set of shared weights. However, our observations reveal a previously unseen and severe bit-width interference phenomenon among highly coupled weights during optimization, leading to considerable performance degradation under a high compression ratio. To tackle this problem, we first design a bit-width scheduler to dynamically freeze the most turbulent bit-width of layers during training, to ensure the rest bit-widths converged properly. Then, taking inspiration from information theory, we present an information distortion mitigation technique to align the behavior of the bad-performing bit-widths to the well-performing ones. In the second stage, an inference-only greedy search scheme is devised to evaluate the goodness of configurations without introducing any additional training costs. Extensive experiments on three representative models and three datasets demonstrate the effectiveness of the proposed method. Code can be available on hrefhttps://www.github.com/1hunters/retraining-free-quantizationhttps://github.com/1hunters/retraining-free-quantization.