REx: Data-Free Residual Quantization Error Expansion

• URL: http://arxiv.org/abs/2203.14645v3
• Date: Mon, 29 May 2023 13:10:33 GMT
• Title: REx: Data-Free Residual Quantization Error Expansion
• Authors: Edouard Yvinec and Arnaud Dapgony and Matthieu Cord and Kevin Bailly
• Abstract summary: Deep neural networks (DNNs) are ubiquitous in computer vision and natural language processing, but suffer from high inference cost. With the growing concerns on privacy rights, we focus our efforts on data-free methods. We propose REx, a quantization method that leverages residual error expansion, along with group sparsity and an ensemble approximation for better parallelization.
• Score: 32.87131159997359
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks (DNNs) are ubiquitous in computer vision and natural language processing, but suffer from high inference cost. This problem can be addressed by quantization, which consists in converting floating point operations into a lower bit-width format. With the growing concerns on privacy rights, we focus our efforts on data-free methods. However, such techniques suffer from their lack of adaptability to the target devices, as a hardware typically only support specific bit widths. Thus, to adapt to a variety of devices, a quantization method shall be flexible enough to find good accuracy v.s. speed trade-offs for every bit width and target device. To achieve this, we propose REx, a quantization method that leverages residual error expansion, along with group sparsity and an ensemble approximation for better parallelization. REx is backed off by strong theoretical guarantees and achieves superior performance on every benchmarked application (from vision to NLP tasks), architecture (ConvNets, transformers) and bit-width (from int8 to ternary quantization).

Related papers

• PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions [23.1120983784623]
  PIPE is a quantization method that leverages residual error expansion, along with group sparsity and an ensemble approximation for better parallelization. It achieves superior performance on every benchmarked application (from vision to NLP tasks), architecture (ConvNets, transformers) and bit-width.
  arXiv  Detail & Related papers  (2023-11-27T13:29:34Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures [68.91874045918112]
  adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks. We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
  arXiv  Detail & Related papers  (2023-03-25T14:40:59Z)
• Scaled Quantization for the Vision Transformer [0.0]
  Quantization using a small number of bits shows promise for reducing latency and memory usage in deep neural networks. This paper proposes a robust method for the full integer quantization of vision transformer networks without requiring any intermediate floating-point computations.
  arXiv  Detail & Related papers  (2023-03-23T18:31:21Z)
• A Practical Mixed Precision Algorithm for Post-Training Quantization [15.391257986051249]
  Mixed-precision quantization is a promising solution to find a better performance-efficiency trade-off than homogeneous quantization. We present a simple post-training mixed precision algorithm that only requires a small unlabeled calibration dataset. We show that we can find mixed precision networks that provide a better trade-off between accuracy and efficiency than their homogeneous bit-width equivalents.
  arXiv  Detail & Related papers  (2023-02-10T17:47:54Z)
• ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization [31.494669469303954]
  We propose a fixed-length adaptive numerical data type called ANT to achieve low-bit quantization with tiny hardware overheads. Our design results in 2.8$times$ speedup and 2.5$times$ energy efficiency improvement over the state-of-the-art quantization accelerators.
  arXiv  Detail & Related papers  (2022-08-30T14:12:49Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration [83.84684675841167]
  We propose a novel encoding scheme using -1, +1 to decompose quantized neural networks (QNNs) into multi-branch binary networks. We validate the effectiveness of our method on large-scale image classification, object detection, and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-06-18T03:11:15Z)
• AQD: Towards Accurate Fully-Quantized Object Detection [94.06347866374927]
  We propose an Accurate Quantized object Detection solution, termed AQD, to get rid of floating-point computation. Our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes.
  arXiv  Detail & Related papers  (2020-07-14T09:07:29Z)
• Efficient Integer-Arithmetic-Only Convolutional Neural Networks [87.01739569518513]
  We replace conventional ReLU with Bounded ReLU and find that the decline is due to activation quantization. Our integer networks achieve equivalent performance as the corresponding FPN networks, but have only 1/4 memory cost and run 2x faster on modern GPU.
  arXiv  Detail & Related papers  (2020-06-21T08:23:03Z)

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.