# Loss Aware Post-training Quantization

arXiv: https://arxiv.org/abs/1911.07190 · HTML: https://mlsanity.com/paper/1911.07190/

## Key facts

- Cited by 97 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2019.

## Built on by (most cited first, 30 of 97)

- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning](https://mlsanity.com/paper/2208.11580/) (2022)
- [Post-training Quantization on Diffusion Models](https://mlsanity.com/paper/2211.15736/) (2022)
- [Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models](https://mlsanity.com/paper/2209.13325/) (2022)
- [QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization](https://mlsanity.com/paper/2203.05740/) (2022)
- [Overcoming Oscillations in Quantization-Aware Training](https://mlsanity.com/paper/2203.11086/) (2022)
- [OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models](https://mlsanity.com/paper/2306.02272/) (2023)
- [Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks](https://mlsanity.com/paper/2102.08124/) (2021)
- [PD-Quant: Post-Training Quantization based on Prediction Difference Metric](https://mlsanity.com/paper/2212.07048/) (2022)
- [QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning](https://mlsanity.com/paper/2402.03666/) (2024)
- [FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization](https://mlsanity.com/paper/2306.00317/) (2023)
- [Towards Accurate Post-training Quantization for Diffusion Models](https://mlsanity.com/paper/2305.18723/) (2023)
- [Q-VLM: Post-training Quantization for Large Vision-Language Models](https://mlsanity.com/paper/2410.08119/) (2024)
- [Towards Efficient Post-training Quantization of Pre-trained Language Models](https://mlsanity.com/paper/2109.15082/) (2021)
- [Auto-Split: A General Framework of Collaborative Edge-Cloud AI](https://mlsanity.com/paper/2108.13041/) (2021)
- [Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats](https://mlsanity.com/paper/2112.10769/) (2021)
- [Instance-Aware Group Quantization for Vision Transformers](https://mlsanity.com/paper/2404.00928/) (2024)
- [It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher](https://mlsanity.com/paper/2203.17008/) (2022)
- [Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers](https://mlsanity.com/paper/2308.10814/) (2023)
- [Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective](https://mlsanity.com/paper/2303.11906/) (2023)
- [On Efficient Variants of Segment Anything Model: A Survey](https://mlsanity.com/paper/2410.04960/) (2024)
- [The Effect of Model Compression on Fairness in Facial Expression Recognition](https://mlsanity.com/paper/2201.01709/) (2022)
- [Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices](https://mlsanity.com/paper/2206.10844/) (2022)
- [Poster: Self-Supervised Quantization-Aware Knowledge Distillation](https://mlsanity.com/paper/2309.13220/) (2023)
- [QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception](https://mlsanity.com/paper/2509.03704/) (2025)
- [HPTQ: Hardware-Friendly Post Training Quantization](https://mlsanity.com/paper/2109.09113/) (2021)
- [Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression](https://mlsanity.com/paper/2211.02854/) (2022)
- [EQ-Net: Elastic Quantization Neural Networks](https://mlsanity.com/paper/2308.07650/) (2023)
- [IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models](https://mlsanity.com/paper/2410.21759/) (2024)

## Abstract (arXiv)

Neural network quantization enables the deployment of large models on resource-constrained devices. Current post-training quantization methods fall short in terms of accuracy for INT4 (or lower) but provide reasonable accuracy for INT8 (or above). In this work, we study the effect of quantization on the structure of the loss landscape. Additionally, we show that the structure is flat and separable for mild quantization, enabling straightforward post-training quantization methods to achieve good results. We show that with more aggressive quantization, the loss landscape becomes highly non-separable with steep curvature, making the selection of quantization parameters more challenging. Armed with this understanding, we design a method that quantizes the layer parameters jointly, enabling significant accuracy improvement over current post-training quantization methods. Reference implementation is available at https://github.com/ynahshan/nn-quantization-pytorch/tree/master/lapq