mlsanityData to 7 Oct 2026

Up or Down? Adaptive Rounding for Post-Training Quantization

arXiv 2004.10568 ↗First posted 22 Apr 2020cs.LG cs.CV stat.MLcited by 600

Not on the map. Why?

Cited by 58 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

When quantizing neural networks, assigning each floating-point weight to its nearest fixed-point value is the predominant approach. We find that, perhaps surprisingly, this is not the best we can do. In this paper, we propose AdaRound, a better weight-rounding mechanism for post-training quantization that adapts to the data and the task loss. AdaRound is fast, does not require fine-tuning of the network, and only uses a small amount of unlabelled data. We start by theoretically analyzing the rounding problem for a pre-trained neural network. By approximating the task loss with a Taylor series expansion, the rounding task is posed as a quadratic unconstrained binary optimization problem. We simplify this to a layer-wise local loss and propose to optimize this loss with a soft relaxation. AdaRound not only outperforms rounding-to-nearest by a significant margin but also establishes a new state-of-the-art for post-training quantization on several networks and tasks. Without fine-tuning, we can quantize the weights of Resnet18 and Resnet50 to 4 bits while staying within an accuracy loss of 1%.

Key facts. Cited by 600 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 39; 2022: 52; 2023: 100; 2024: 134; 2025: 141; 2026: 134.

600 papers.

Sort:

By area:

  1. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  2. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  3. 2023SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shotcited by 1,090
  4. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  5. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 517
  6. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  7. 2021A White Paper on Neural Network Quantizationcited by 453
  8. 2024SpinQuant: LLM quantization with learned rotationscited by 446
  9. 2023OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Modelscited by 403
  10. 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 397
  11. 2023SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compressioncited by 359
  12. 2024QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebookscited by 354
38 more
  1. 2022Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruningcited by 317
  2. 2021Post-Training Quantization for Vision Transformercited by 274
  3. 2023Q-Diffusion: Quantizing Diffusion Modelscited by 266
  4. 2023A Survey on Model Compression for Large Language Modelscited by 263
  5. 2024Extreme Compression of Large Language Models via Additive Quantizationcited by 223
  6. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 216
  7. 2022Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Modelscited by 176
  8. 2022QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantizationcited by 175
  9. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 167
  10. 2024DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMscited by 165
  11. 2021Implicit Neural Representations for Image Compressioncited by 161
  12. 2022A Fast Post-Training Pruning Framework for Transformerscited by 161
  13. 2021FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformercited by 148
  14. 2023Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothingcited by 147
  15. 2021Understanding and Overcoming the Challenges of Efficient Transformer Quantizationcited by 139
  16. 2021Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networkscited by 134
  17. 2022RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision Transformerscited by 134
  18. 2024EfficientQAT: Efficient Quantization-Aware Training for Large Language Modelscited by 123
  19. 2024MiniCache: KV Cache Compression in Depth Dimension for Large Language Modelscited by 122
  20. 2022Overcoming Oscillations in Quantization-Aware Trainingcited by 116
  21. 2024FlatQuant: Flatness Matters for LLM Quantizationcited by 116
  22. 2023OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Modelscited by 113
  23. 2023RPTQ: Reorder-based Post-training Quantization for Large Language Modelscited by 112
  24. 2024ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generationcited by 110
  25. 2021Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Maskscited by 103
  26. 2022LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Modelscited by 98
  27. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  28. 2024Q-DiT: Accurate Post-Training Quantization for Diffusion Transformerscited by 91
  29. 2023Fast Inference of Mixture-of-Experts Language Models with Offloadingcited by 88
  30. 2022FP8 Quantization: The Power of the Exponentcited by 87
  31. 2024QTIP: Quantization with Trellises and Incoherence Processingcited by 86
  32. 2023Temporal Dynamic Quantization for Diffusion Modelscited by 81
  33. 2024GPTVQ: The Blessing of Dimensionality for LLM Quantizationcited by 78
  34. 2023EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Modelscited by 77
  35. 2024PTQ4DiT: Post-training Quantization for Diffusion Transformerscited by 77
  36. 2022PD-Quant: Post-Training Quantization based on Prediction Difference Metriccited by 73
  37. 2023TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Modelscited by 67
  38. 2023LLM-FP4: 4-Bit Floating-Point Quantized Transformerscited by 65

50 most cited of 600 All 600 (JSON)