Beyond round-to-nearest: AdaRound, BRECQ and LSQ
Optional · supplementary note 6 of 6 for DLCV 01C · Model Compression and Efficient Inference. Nothing in the main text depends on it; citation numbers refer to the reference list at the bottom of this page.
Navigate: this page and this track: Navigate: this page and this track
This note describes three methods that improve on the basic recipe of “choose a range, round to the nearest grid point”.
AdaRound questions the rounding step itself. Rounding every weight to its nearest grid point minimizes the error of each weight separately, but not the error of the layer’s output, because the errors of different weights interact through the inputs. Nagel et al. approximate the task loss with a Taylor expansion, which turns the up-or-down decision for every weight into a binary optimization problem; they simplify it to a layer-wise loss on the layer’s output and solve a soft relaxation on a small amount of unlabeled data. They report 4-bit weights for ResNet-18 and ResNet-50 within 1% of float accuracy without fine-tuning [20]. Each weight still moves to one of its two neighbouring grid points, so the stored format does not change.
BRECQ reconstructs blocks instead of single layers: it quantizes a network block by block and optimizes each quantized block so that its output matches the output of the float block. From an analysis of the second-order error, the authors argue that blocks balance cross-layer dependencies against overfitting to the small calibration set, and they add mixed precision based on approximate sensitivities [71].
LSQ applies to quantization-aware training. Instead of setting the scale of each quantizer from statistics, it makes a trainable parameter and estimates its gradient through the quantizer, scaled so that the step size learns at a suitable pace relative to the weights. The authors report ImageNet models with weights and activations at 2, 3 or 4 bits, and 3-bit models that reach the full-precision baseline [72]. A pitfall shared by all learnable quantizer parameters: Nagel et al. note that with SGD-type optimizers their learning rate must be lowered relative to the other parameters, which adaptive optimizers such as Adam avoid [15].
References
- M. Dehghani, A. Arnab, L. Beyer, A. Vaswani and Y. Tay, “The efficiency misnomer,” ICLR, 2022. arXiv
- S. Williams, A. Waterman and D. Patterson, “Roofline: an insightful visual performance model for multicore architectures,” Communications of the ACM, vol. 52, no. 4, pp. 65–76, 2009. doi
- Z. Liu, M. Sun, T. Zhou, G. Huang and T. Darrell, “Rethinking the value of network pruning,” ICLR, 2019. arXiv
- D. Blalock, J. J. Gonzalez Ortiz, J. Frankle and J. Guttag, “What is the state of neural network pruning?,” MLSys, 2020. arXiv
- H. Li, A. Kadav, I. Durdanovic, H. Samet and H. P. Graf, “Pruning filters for efficient ConvNets,” ICLR, 2017. arXiv
- A. Mishra, J. Albericio Latorre, J. Pool, D. Stosic, D. Stosic, G. Venkatesh, C. Yu and P. Micikevicius, “Accelerating sparse deep neural networks,” arXiv:2104.08378, 2021. arXiv
- Z. Liu, J. Li, Z. Shen, G. Huang, S. Yan and C. Zhang, “Learning efficient convolutional networks through network slimming,” ICCV, 2017. arXiv
- T. Hoefler, D. Alistarh, T. Ben-Nun, N. Dryden and A. Peste, “Sparsity in deep learning: pruning and growth for efficient inference and training in neural networks,” Journal of Machine Learning Research, vol. 22, no. 241, pp. 1–124, 2021. paper
- G. Fang, X. Ma, M. Song, M. B. Mi and X. Wang, “DepGraph: towards any structural pruning,” CVPR, 2023. doi arXiv
- S. Han, J. Pool, J. Tran and W. J. Dally, “Learning both weights and connections for efficient neural networks,” NeurIPS (NIPS), 2015. arXiv
- S. Han, H. Mao and W. J. Dally, “Deep compression: compressing deep neural networks with pruning, trained quantization and Huffman coding,” ICLR, 2016. arXiv
- M. Zhu and S. Gupta, “To prune, or not to prune: exploring the efficacy of pruning for model compression,” arXiv:1710.01878, 2017. arXiv
- J. Frankle and M. Carbin, “The lottery ticket hypothesis: finding sparse, trainable neural networks,” ICLR, 2019. arXiv
- J. Frankle, G. K. Dziugaite, D. M. Roy and M. Carbin, “Linear mode connectivity and the lottery ticket hypothesis,” ICML, 2020. arXiv
- M. Nagel, M. Fournarakis, R. A. Amjad, Y. Bondarenko, M. van Baalen and T. Blankevoort, “A white paper on neural network quantization,” arXiv:2106.08295, 2021. arXiv
- B. Jacob, S. Kligys, B. Chen, M. Zhu, M. Tang, A. Howard, H. Adam and D. Kalenichenko, “Quantization and training of neural networks for efficient integer-arithmetic-only inference,” CVPR, 2018. doi arXiv
- M. Nagel, M. van Baalen, T. Blankevoort and M. Welling, “Data-free quantization through weight equalization and bias correction,” ICCV, 2019. arXiv
- T. Dettmers, M. Lewis, Y. Belkada and L. Zettlemoyer, “LLM.int8(): 8-bit matrix multiplication for transformers at scale,” NeurIPS, 2022. arXiv
- G. Xiao, J. Lin, M. Seznec, H. Wu, J. Demouth and S. Han, “SmoothQuant: accurate and efficient post-training quantization for large language models,” ICML, 2023. arXiv
- M. Nagel, R. A. Amjad, M. van Baalen, C. Louizos and T. Blankevoort, “Up or down? Adaptive rounding for post-training quantization,” ICML, 2020. arXiv
- Y. Bengio, N. Léonard and A. Courville, “Estimating or propagating gradients through stochastic neurons for conditional computation,” arXiv:1308.3432, 2013. arXiv
- Z. Dong, Z. Yao, A. Gholami, M. W. Mahoney and K. Keutzer, “HAWQ: Hessian aware quantization of neural networks with mixed-precision,” ICCV, 2019. arXiv
- K. Wang, Z. Liu, Y. Lin, J. Lin and S. Han, “HAQ: hardware-aware automated quantization with mixed precision,” CVPR, 2019. arXiv
- P. Micikevicius et al., “FP8 formats for deep learning,” arXiv:2209.05433, 2022. arXiv
- G. Hinton, O. Vinyals and J. Dean, “Distilling the knowledge in a neural network,” NIPS Deep Learning Workshop, 2014; arXiv:1503.02531. arXiv
- L. J. Ba and R. Caruana, “Do deep nets really need to be deep?,” NeurIPS (NIPS), 2014. arXiv
- A. Romero, N. Ballas, S. E. Kahou, A. Chassang, C. Gatta and Y. Bengio, “FitNets: hints for thin deep nets,” ICLR, 2015. arXiv
- S. Zagoruyko and N. Komodakis, “Paying more attention to attention: improving the performance of convolutional neural networks via attention transfer,” ICLR, 2017. arXiv
- J. Gou, B. Yu, S. J. Maybank and D. Tao, “Knowledge distillation: a survey,” International Journal of Computer Vision, vol. 129, no. 6, pp. 1789–1819, 2021. doi
- L. Beyer, X. Zhai, A. Royer, L. Markeeva, R. Anil and A. Kolesnikov, “Knowledge distillation: a good teacher is patient and consistent,” CVPR, 2022. arXiv
- J. H. Cho and B. Hariharan, “On the efficacy of knowledge distillation,” ICCV, 2019. arXiv
- H. Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles and H. Jégou, “Training data-efficient image transformers & distillation through attention,” ICML, 2021. arXiv
- R. Denton, W. Zaremba, J. Bruna, Y. LeCun and R. Fergus, “Exploiting linear structure within convolutional networks for efficient evaluation,” NeurIPS (NIPS), 2014. arXiv
- M. Jaderberg, A. Vedaldi and A. Zisserman, “Speeding up convolutional neural networks with low rank expansions,” BMVC, 2014. arXiv
- X. Zhang, J. Zou, K. He and J. Sun, “Accelerating very deep convolutional networks for classification and detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 10, pp. 1943–1955, 2016. doi arXiv
- A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto and H. Adam, “MobileNets: efficient convolutional neural networks for mobile vision applications,” arXiv:1704.04861, 2017. arXiv
- M. Sandler, A. Howard, M. Zhu, A. Zhmoginov and L.-C. Chen, “MobileNetV2: inverted residuals and linear bottlenecks,” CVPR, 2018. arXiv
- M. Tan and Q. V. Le, “EfficientNet: rethinking model scaling for convolutional neural networks,” ICML, 2019. arXiv
- X. Ding, X. Zhang, N. Ma, J. Han, G. Ding and J. Sun, “RepVGG: making VGG-style ConvNets great again,” CVPR, 2021. arXiv
- C. Li et al., “YOLOv6: a single-stage object detection framework for industrial applications,” arXiv:2209.02976, 2022. arXiv
- T. Elsken, J. H. Metzen and F. Hutter, “Neural architecture search: a survey,” Journal of Machine Learning Research, vol. 20, pp. 1–21, 2019. arXiv
- B. Zoph and Q. V. Le, “Neural architecture search with reinforcement learning,” ICLR, 2017. arXiv
- H. Pham, M. Y. Guan, B. Zoph, Q. V. Le and J. Dean, “Efficient neural architecture search via parameter sharing,” ICML, 2018. arXiv
- H. Liu, K. Simonyan and Y. Yang, “DARTS: differentiable architecture search,” ICLR, 2019. arXiv
- H. Cai, C. Gan, T. Wang, Z. Zhang and S. Han, “Once-for-all: train one network and specialize it for efficient deployment,” ICLR, 2020. arXiv
- M. Tan, B. Chen, R. Pang, V. Vasudevan, M. Sandler, A. Howard and Q. V. Le, “MnasNet: platform-aware neural architecture search for mobile,” CVPR, 2019. arXiv
- H. Cai, L. Zhu and S. Han, “ProxylessNAS: direct neural architecture search on target task and hardware,” ICLR, 2019. arXiv
- B. Wu, X. Dai, P. Zhang, Y. Wang, F. Sun, Y. Wu, Y. Tian, P. Vajda, Y. Jia and K. Keutzer, “FBNet: hardware-aware efficient ConvNet design via differentiable neural architecture search,” CVPR, 2019. doi arXiv
- L. Li and A. Talwalkar, “Random search and reproducibility for neural architecture search,” UAI, 2019. arXiv
- S. Ioffe and C. Szegedy, “Batch normalization: accelerating deep network training by reducing internal covariate shift,” ICML, 2015. arXiv
- T. Wang, L. Yuan, X. Zhang and J. Feng, “Distilling object detectors with fine-grained feature imitation,” CVPR, 2019. arXiv
- H. Li, C. Yan, S. Lin, X. Zheng, Y. Li, B. Zhang, F. Yang and R. Ji, “PAMS: quantized super-resolution via parameterized max scale,” ECCV, 2020. arXiv
- C. Hong, H. Kim, S. Baik, J. Oh and K. M. Lee, “DAQ: channel-wise distribution-aware quantization for deep image super-resolution networks,” WACV, 2022. arXiv
- B. Ren, Y. Li, N. Mehta, R. Timofte et al., “The ninth NTIRE 2024 efficient super-resolution challenge report,” CVPR Workshops, 2024. doi arXiv
- Z. Yuan, C. Xue, Y. Chen, Q. Wu and G. Sun, “PTQ4ViT: post-training quantization for vision transformers with twin uniform quantization,” ECCV, 2022. doi arXiv
- Z. Liu, Y. Wang, K. Han, S. Ma and W. Gao, “Post-training quantization for vision transformer,” NeurIPS, 2021. arXiv
- X. Li, Y. Liu, L. Lian, H. Yang, Z. Dong, D. Kang, S. Zhang and K. Keutzer, “Q-Diffusion: quantizing diffusion models,” ICCV, 2023. doi arXiv
- Y. Shang, Z. Yuan, B. Xie, B. Wu and Y. Yan, “Post-training quantization on diffusion models,” CVPR, 2023. arXiv
- A. Kirillov et al., “Segment anything,” ICCV, 2023. doi arXiv
- C. Zhang, D. Han, Y. Qiao, J. U. Kim, S.-H. Bae, S. Lee and C. S. Hong, “Faster segment anything: towards lightweight SAM for mobile applications,” arXiv:2306.14289, 2023. arXiv
- Y. Xiong et al., “EfficientSAM: leveraged masked image pretraining for efficient segment anything,” CVPR, 2024. doi arXiv
- Y. Cheng, D. Wang, P. Zhou and T. Zhang, “Model compression and acceleration for deep neural networks: the principles, progress, and challenges,” IEEE Signal Processing Magazine, vol. 35, no. 1, pp. 126–136, 2018. doi arXiv
- G. Menghani, “Efficient deep learning: a survey on making deep learning models smaller, faster, and better,” ACM Computing Surveys, vol. 55, no. 12, pp. 1–37, 2023. doi arXiv
- A. Gholami, S. Kim, Z. Dong, Z. Yao, M. W. Mahoney and K. Keutzer, “A survey of quantization methods for efficient neural network inference,” book chapter in Low-Power Computer Vision; arXiv:2103.13630, 2021. arXiv
- H. Cheng, M. Zhang and J. Q. Shi, “A survey on deep neural network pruning: taxonomy, comparison, analysis, and recommendations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 12, pp. 10558–10578, 2024. doi arXiv
- L. Wang and K.-J. Yoon, “Knowledge distillation and student-teacher learning for visual intelligence: a review and new outlooks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 6, pp. 3048–3068, 2022. doi arXiv
- C. White, M. Safari, R. Sukthanker, B. Ru, T. Elsken, A. Zela, D. Dey and F. Hutter, “Neural architecture search: insights from 1000 papers,” arXiv:2301.08727, 2023. arXiv
- E. Frantar, S. Ashkboos, T. Hoefler and D. Alistarh, “GPTQ: accurate post-training quantization for generative pre-trained transformers,” ICLR, 2023. arXiv
- J. Lin, J. Tang, H. Tang, S. Yang, W.-M. Chen, W.-C. Wang, G. Xiao, X. Dang, C. Gan and S. Han, “AWQ: activation-aware weight quantization for LLM compression and acceleration,” MLSys, 2024. arXiv
- M. Li, Y. Lin, Z. Zhang, T. Cai, X. Li, J. Guo, E. Xie, C. Meng, J.-Y. Zhu and S. Han, “SVDQuant: absorbing outliers by low-rank components for 4-bit diffusion models,” ICLR, 2025. arXiv
- Y. Li, R. Gong, X. Tan, Y. Yang, P. Hu, Q. Zhang, F. Yu, W. Wang and S. Gu, “BRECQ: pushing the limit of post-training quantization by block reconstruction,” ICLR, 2021. arXiv
- S. K. Esser, J. L. McKinstry, D. Bablani, R. Appuswamy and D. S. Modha, “Learned step size quantization,” ICLR, 2020. arXiv