Hadamard Domain Training with Integers for Class Incremental Quantized Learning

• URL: http://arxiv.org/abs/2310.03675v1
• Date: Thu, 5 Oct 2023 16:52:59 GMT
• Title: Hadamard Domain Training with Integers for Class Incremental Quantized Learning
• Authors: Martin Schiemer, Clemens JS Schaefer, Jayden Parker Vap, Mark James Horeni, Yu Emma Wang, Juan Ye, and Siddharth Joshi
• Abstract summary: Continual learning can be cost-prohibitive for resource-constraint edge platforms. We propose a technique that transforms to enable low-precision training with only integer matrix multiplications. We achieve less than 0.5% and 3% accuracy degradation while we quantize all matrix multiplications inputs down to 4-bits with 8-bit accumulators.
• Score: 1.4416751609100908
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning is a desirable feature in many modern machine learning applications, which allows in-field adaptation and updating, ranging from accommodating distribution shift, to fine-tuning, and to learning new tasks. For applications with privacy and low latency requirements, the compute and memory demands imposed by continual learning can be cost-prohibitive for resource-constraint edge platforms. Reducing computational precision through fully quantized training (FQT) simultaneously reduces memory footprint and increases compute efficiency for both training and inference. However, aggressive quantization especially integer FQT typically degrades model accuracy to unacceptable levels. In this paper, we propose a technique that leverages inexpensive Hadamard transforms to enable low-precision training with only integer matrix multiplications. We further determine which tensors need stochastic rounding and propose tiled matrix multiplication to enable low-bit width accumulators. We demonstrate the effectiveness of our technique on several human activity recognition datasets and CIFAR100 in a class incremental learning setting. We achieve less than 0.5% and 3% accuracy degradation while we quantize all matrix multiplications inputs down to 4-bits with 8-bit accumulators.

Related papers

• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Is Integer Arithmetic Enough for Deep Learning Training? [2.9136421025415205]
  replacing floating-point arithmetic with low-bit integer arithmetic is a promising approach to save energy, memory footprint, and latency of deep learning models. We propose a fully functional integer training pipeline including forward pass, back-propagation, and gradient descent. Our experimental results show that our proposed method is effective in a wide variety of tasks such as classification (including vision transformers), object detection, and semantic segmentation.
  arXiv  Detail & Related papers  (2022-07-18T22:36:57Z)
• Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations [2.3488056916440856]
  We propose a novel algorithm to find efficient low-rankworks. Theseworks are determined and adapted already during the training phase. Our method automatically and dynamically adapts the ranks during training to achieve a desired approximation accuracy.
  arXiv  Detail & Related papers  (2022-05-26T18:18:12Z)
• Mesa: A Memory-saving Training Framework for Transformers [58.78933015299703]
  We present Mesa, a memory-saving training framework for Transformers. Mesa uses exact activations during forward pass while storing a low-precision version of activations to reduce memory consumption during training. Experiments on ImageNet, CIFAR-100 and ADE20K demonstrate that Mesa can reduce half of the memory footprints during training.
  arXiv  Detail & Related papers  (2021-11-22T11:23:01Z)
• Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds [99.23098204458336]
  Certified robustness is a desirable property for deep neural networks in safety-critical applications. We show that our method consistently outperforms state-of-the-art methods on MNIST and TinyNet datasets.
  arXiv  Detail & Related papers  (2021-11-02T06:44:10Z)
• LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time [57.52251547365967]
  We propose a method for training a "compressible subspace" of neural networks that contains a fine-grained spectrum of models. We present results for achieving arbitrarily fine-grained accuracy-efficiency trade-offs at inference time for structured and unstructured sparsity. Our algorithm extends to quantization at variable bit widths, achieving accuracy on par with individually trained networks.
  arXiv  Detail & Related papers  (2021-10-08T17:03:34Z)
• ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training [68.63354877166756]
  ActNN is a memory-efficient training framework that stores randomly quantized activations for back propagation. ActNN reduces the memory footprint of the activation by 12x, and it enables training with a 6.6x to 14x larger batch size.
  arXiv  Detail & Related papers  (2021-04-29T05:50:54Z)
• Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition [65.7040645560855]
  We propose Q-ASR, an integer-only, zero-shot quantization scheme for ASR models. We show negligible WER change as compared to the full-precision baseline models. Q-ASR exhibits a large compression rate of more than 4x with small WER degradation.
  arXiv  Detail & Related papers  (2021-03-31T06:05:40Z)
• Memristive Stochastic Computing for Deep Learning Parameter Optimization [1.6344851071810071]
  Computing (SC) is a computing paradigm that allows for the low-cost and low-power of various arithmetic operations using bit streams and digital logic. We demonstrate that in using a 40-nm Complementary Metal Oxide Semiconductor (CMOS) process our scalable architecture occupies 1.55mm$2$ and consumes approximately 167$mu$W when optimizing parameters of a Convolutional Neural Network (CNN) while it is being trained for a character recognition task, observing no notable reduction in accuracy post-training.
  arXiv  Detail & Related papers  (2021-03-11T07:10:32Z)
• Improving compute efficacy frontiers with SliceOut [31.864949424541344]
  We introduce SliceOut -- a dropout-inspired scheme to train deep learning models faster without impacting final test accuracy. At test time, turning off SliceOut performs an implicit ensembling across a linear number of architectures that preserves test accuracy. This leads to faster processing of large computational workloads overall, and significantly reduce the resulting energy consumption and CO2emissions.
  arXiv  Detail & Related papers  (2020-07-21T15:59:09Z)

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.