Oscillations Make Neural Networks Robust to Quantization

• URL: http://arxiv.org/abs/2502.00490v1
• Date: Sat, 01 Feb 2025 16:39:58 GMT
• Title: Oscillations Make Neural Networks Robust to Quantization
• Authors: Jonathan Wenshøj, Bob Pepin, Raghavendra Selvan,
• Abstract summary: We show that oscillations in Quantization Aware Training (QAT) are undesirable artifacts caused by the Straight-Through Estimator (STE) We propose a novel regularization method that induces oscillations to improve quantization.
• Score: 0.16385815610837165
• License:
• Abstract: We challenge the prevailing view that oscillations in Quantization Aware Training (QAT) are merely undesirable artifacts caused by the Straight-Through Estimator (STE). Through theoretical analysis of QAT in linear models, we demonstrate that the gradient of the loss function can be decomposed into two terms: the original full-precision loss and a term that causes quantization oscillations. Based on these insights, we propose a novel regularization method that induces oscillations to improve quantization robustness. Contrary to traditional methods that focuses on minimizing the effects of oscillations, our approach leverages the beneficial aspects of weight oscillations to preserve model performance under quantization. Our empirical results on ResNet-18 and Tiny ViT demonstrate that this counter-intuitive strategy matches QAT accuracy at >= 3-bit weight quantization, while maintaining close to full precision accuracy at bits greater than the target bit. Our work therefore provides a new perspective on model preparation for quantization, particularly for finding weights that are robust to changes in the bit of the quantizer -- an area where current methods struggle to match the accuracy of QAT at specific bits.

Related papers

• Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction [48.740630807085566]
  Post-training quantization (PTQ) for vision transformers (ViTs) has received increasing attention from both academic and industrial communities. Current methods fail to account for the complex interactions between quantized weights and activations, resulting in significant quantization errors and suboptimal performance. This paper presents ERQ, an innovative two-step PTQ method specifically crafted to reduce quantization errors arising from activation and weight quantization sequentially.
  arXiv  Detail & Related papers  (2024-07-09T12:06:03Z)
• WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More [55.0856305773081]
  Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on the quantization of LLMs, a technique that reduces memory consumption by converting model parameters and activations into low-bit integers.
  arXiv  Detail & Related papers  (2024-02-19T11:33:21Z)
• On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks [52.97107229149988]
  We propose an On-Chip Hardware-Aware Quantization framework, performing hardware-aware mixed-precision quantization on deployed edge devices. For efficiency metrics, we built an On-Chip Quantization Aware pipeline, which allows the quantization process to perceive the actual hardware efficiency of the quantization operator. For accuracy metrics, we propose Mask-Guided Quantization Estimation technology to effectively estimate the accuracy impact of operators in the on-chip scenario.
  arXiv  Detail & Related papers  (2023-09-05T04:39:34Z)
• Oscillation-free Quantization for Low-bit Vision Transformers [36.64352091626433]
  Weight oscillation is an undesirable side effect of quantization-aware training. We propose three techniques to improve quantization compared to the prevalent learnable-scale-based method. Our algorithms consistently achieve substantial accuracy improvement on ImageNet.
  arXiv  Detail & Related papers  (2023-02-04T17:40:39Z)
• Symmetry Regularization and Saturating Nonlinearity for Robust Quantization [5.1779694507922835]
  We present three insights to robustify a network against quantization. We propose two novel methods called symmetry regularization (SymReg) and saturating nonlinearity (SatNL) Applying the proposed methods during training can enhance the robustness of arbitrary neural networks against quantization.
  arXiv  Detail & Related papers  (2022-07-31T02:12:28Z)
• Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss [4.877532217193618]
  Existing quantization techniques rely heavily on experience and "fine-tuning" skills. This study provides a methodology for acquiring a mixed-precise quantization model with a lower loss than the full precision model. In particular, we will demonstrate that neural networks with massive identity mappings are resistant to the quantization method.
  arXiv  Detail & Related papers  (2022-07-20T10:55:34Z)
• Overcoming Oscillations in Quantization-Aware Training [18.28657022169428]
  When training neural networks with simulated quantization, quantized weights can, rather unexpectedly, oscillate between two grid-points. We show that it can lead to a significant accuracy degradation due to wrongly estimated batch-normalization statistics. We propose two novel QAT algorithms to overcome oscillations during training: oscillation dampening and iterative weight freezing.
  arXiv  Detail & Related papers  (2022-03-21T16:07:42Z)
• Learnable Companding Quantization for Accurate Low-bit Neural Networks [3.655021726150368]
  Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed. It is still hard for extremely low-bit models to achieve accuracy comparable with that of full-precision models. We propose learnable companding quantization (LCQ) as a novel non-uniform quantization method for 2-, 3-, and 4-bit models.
  arXiv  Detail & Related papers  (2021-03-12T09:06:52Z)
• DAQ: Distribution-Aware Quantization for Deep Image Super-Resolution Networks [49.191062785007006]
  Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs. Existing works either suffer from a severe performance drop in ultra-low precision of 4 or lower bit-widths, or require a heavy fine-tuning process to recover the performance. We propose a novel distribution-aware quantization scheme (DAQ) which facilitates accurate training-free quantization in ultra-low precision.
  arXiv  Detail & Related papers  (2020-12-21T10:19:42Z)
• A Statistical Framework for Low-bitwidth Training of Deep Neural Networks [70.77754244060384]
  Fully quantized training (FQT) uses low-bitwidth hardware by quantizing the activations, weights, and gradients of a neural network model. One major challenge with FQT is the lack of theoretical understanding, in particular of how gradient quantization impacts convergence properties.
  arXiv  Detail & Related papers  (2020-10-27T13:57:33Z)
• Gradient $\ell_1$ Regularization for Quantization Robustness [70.39776106458858]
  We derive a simple regularization scheme that improves robustness against post-training quantization. By training quantization-ready networks, our approach enables storing a single set of weights that can be quantized on-demand to different bit-widths.
  arXiv  Detail & Related papers  (2020-02-18T12:31:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.