Block-Wise Dynamic-Precision Neural Network Training Acceleration via Online Quantization Sensitivity Analytics

• URL: http://arxiv.org/abs/2210.17047v1
• Date: Mon, 31 Oct 2022 03:54:16 GMT
• Title: Block-Wise Dynamic-Precision Neural Network Training Acceleration via Online Quantization Sensitivity Analytics
• Authors: Ruoyang Liu, Chenhan Wei, Yixiong Yang, Wenxun Wang, Huazhong Yang, Yongpan Liu
• Abstract summary: We propose DYNASTY, a block-wise dynamic-precision neural network training framework. DYNASTY provides accurate data sensitivity information through fast online analytics, and maintains stable training convergence with an adaptive bit-width map generator. Compared to 8-bit quantization baseline, DYNASTY brings up to $5.1times$ speedup and $4.7times$ energy consumption reduction with no accuracy drop and negligible hardware overhead.
• Score: 8.373265629267257
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Data quantization is an effective method to accelerate neural network training and reduce power consumption. However, it is challenging to perform low-bit quantized training: the conventional equal-precision quantization will lead to either high accuracy loss or limited bit-width reduction, while existing mixed-precision methods offer high compression potential but failed to perform accurate and efficient bit-width assignment. In this work, we propose DYNASTY, a block-wise dynamic-precision neural network training framework. DYNASTY provides accurate data sensitivity information through fast online analytics, and maintains stable training convergence with an adaptive bit-width map generator. Network training experiments on CIFAR-100 and ImageNet dataset are carried out, and compared to 8-bit quantization baseline, DYNASTY brings up to $5.1\times$ speedup and $4.7\times$ energy consumption reduction with no accuracy drop and negligible hardware overhead.

Related papers

• Gradient-based Automatic Mixed Precision Quantization for Neural Networks On-Chip [0.9187138676564589]
  We present High Granularity Quantization (HGQ), an innovative quantization-aware training method. HGQ fine-tune the per-weight and per-activation precision by making them optimizable through gradient descent. This approach enables ultra-low latency and low power neural networks on hardware capable of performing arithmetic operations.
  arXiv  Detail & Related papers  (2024-05-01T17:18:46Z)
• CorrectNet: Robustness Enhancement of Analog In-Memory Computing for Neural Networks by Error Suppression and Compensation [4.570841222958966]
  We propose a framework to enhance the robustness of neural networks under variations and noise. We show that inference accuracy of neural networks can be recovered from as low as 1.69% under variations and noise.
  arXiv  Detail & Related papers  (2022-11-27T19:13:33Z)
• Online Training Through Time for Spiking Neural Networks [66.7744060103562]
  Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Recent progress in training methods has enabled successful deep SNNs on large-scale tasks with low latency. We propose online training through time (OTTT) for SNNs, which is derived from BPTT to enable forward-in-time learning.
  arXiv  Detail & Related papers  (2022-10-09T07:47:56Z)
• On the Tradeoff between Energy, Precision, and Accuracy in Federated Quantized Neural Networks [68.52621234990728]
  Federated learning (FL) over wireless networks requires balancing between accuracy, energy efficiency, and precision. We propose a quantized FL framework that represents data with a finite level of precision in both local training and uplink transmission. Our framework can reduce energy consumption by up to 53% compared to a standard FL model.
  arXiv  Detail & Related papers  (2021-11-15T17:00:03Z)
• Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update [49.948082497688404]
  Training large-scale deep neural networks (DNNs) currently requires a significant amount of energy, leading to serious environmental impacts. One promising approach to reduce the energy costs is representing DNNs with low-precision numbers. We jointly design a lowprecision training framework involving a logarithmic number system (LNS) and a multiplicative weight update training method, termed LNS-Madam.
  arXiv  Detail & Related papers  (2021-06-26T00:32:17Z)
• Data-free mixed-precision quantization using novel sensitivity metric [6.031526641614695]
  We propose a novel sensitivity metric that considers the effect of quantization error on task loss and interaction with other layers. Our experiments show that the proposed metric better represents quantization sensitivity, and generated data are more feasible to be applied to mixed-precision quantization.
  arXiv  Detail & Related papers  (2021-03-18T07:23:21Z)
• A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning [90.44219200633286]
  We propose a simple yet very effective adversarial fine-tuning approach based on a $textitslow start, fast decay$ learning rate scheduling strategy. Experimental results show that the proposed adversarial fine-tuning approach outperforms the state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet datasets.
  arXiv  Detail & Related papers  (2020-12-25T20:50:15Z)
• FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training [81.85361544720885]
  We propose FracTrain that integrates progressive fractional quantization which gradually increases the precision of activations, weights, and gradients. FracTrain reduces computational cost and hardware-quantified energy/latency of DNN training while achieving a comparable or better (-0.12%+1.87%) accuracy.
  arXiv  Detail & Related papers  (2020-12-24T05:24:10Z)
• 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)
• Dynamic Hard Pruning of Neural Networks at the Edge of the Internet [11.605253906375424]
  Dynamic Hard Pruning (DynHP) technique incrementally prunes the network during training. DynHP enables a tunable size reduction of the final neural network and reduces the NN memory occupancy during training. Freed memory is reused by a emphdynamic batch sizing approach to counterbalance the accuracy degradation caused by the hard pruning strategy.
  arXiv  Detail & Related papers  (2020-11-17T10:23:28Z)

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.