Efficient Neural Compression with Inference-time Decoding

• URL: http://arxiv.org/abs/2406.06237v1
• Date: Mon, 10 Jun 2024 13:07:13 GMT
• Title: Efficient Neural Compression with Inference-time Decoding
• Abstract summary: This paper introduces an approach that combines mixed precision, zero-point quantization and entropy coding to push the compression boundary of Resnets beyond the 1-bit frontier. From an implementation standpoint, a compact decoder architecture features reduced latency, thus allowing for inference-compatible decoding.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper explores the combination of neural network quantization and entropy coding for memory footprint minimization. Edge deployment of quantized models is hampered by the harsh Pareto frontier of the accuracy-to-bitwidth tradeoff, causing dramatic accuracy loss below a certain bitwidth. This accuracy loss can be alleviated thanks to mixed precision quantization, allowing for more flexible bitwidth allocation. However, standard mixed precision benefits remain limited due to the 1-bit frontier, that forces each parameter to be encoded on at least 1 bit of data. This paper introduces an approach that combines mixed precision, zero-point quantization and entropy coding to push the compression boundary of Resnets beyond the 1-bit frontier with an accuracy drop below 1% on the ImageNet benchmark. From an implementation standpoint, a compact decoder architecture features reduced latency, thus allowing for inference-compatible decoding.

Related papers

• Towards Practical Lossless Neural Compression for LiDAR Point Clouds [84.36825469211375]
  extreme sparsity of high-precision geometric details hinders efficient context modeling.<n>Our framework comprises two lightweight modules.<n>Experiments demonstrate competitive compression performance at real-time speed.
  arXiv  Detail & Related papers  (2026-03-26T10:02:07Z)
• Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding [56.066799081747845]
  The ever-growing size of neural networks poses serious challenges on resource-constrained devices.<n>We propose a novel post-training compression framework that combines rate-aware quantization with entropy coding.<n>Our method allows for very fast decoding and is compatible with arbitrary quantization grids.
  arXiv  Detail & Related papers  (2025-05-24T15:52:49Z)
• Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic Programming [7.0146264551420066]
  Quantization is a widely used technique to compress neural networks. MPQ addresses this by assigning varied bit-widths to layers, optimizing the accuracy-efficiency trade-off. We introduce CLADO, a practical sensitivity-based MPQ algorithm that captures crosslayer dependency of quantization error.
  arXiv  Detail & Related papers  (2023-07-11T15:56:00Z)
• The END: An Equivariant Neural Decoder for Quantum Error Correction [73.4384623973809]
  We introduce a data efficient neural decoder that exploits the symmetries of the problem. We propose a novel equivariant architecture that achieves state of the art accuracy compared to previous neural decoders.
  arXiv  Detail & Related papers  (2023-04-14T19:46:39Z)
• Deep Quantum Error Correction [73.54643419792453]
  Quantum error correction codes (QECC) are a key component for realizing the potential of quantum computing. In this work, we efficiently train novel emphend-to-end deep quantum error decoders. The proposed method demonstrates the power of neural decoders for QECC by achieving state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2023-01-27T08:16:26Z)
• Automatic Network Adaptation for Ultra-Low Uniform-Precision Quantization [6.1664476076961146]
  Uniform-precision neural network quantization has gained popularity since it simplifies densely packed arithmetic unit for high computing capability. It ignores heterogeneous sensitivity to the impact of quantization errors across the layers, resulting in sub-optimal inference. This work proposes a novel neural architecture search called neural channel expansion that adjusts the network structure to alleviate accuracy degradation from ultra-low uniform-precision quantization.
  arXiv  Detail & Related papers  (2022-12-21T09:41:25Z)
• OMPQ: Orthogonal Mixed Precision Quantization [64.59700856607017]
  Mixed precision quantization takes advantage of hardware's multiple bit-width arithmetic operations to unleash the full potential of network quantization. We propose to optimize a proxy metric, the concept of networkity, which is highly correlated with the loss of the integer programming. This approach reduces the search time and required data amount by orders of magnitude, with little compromise on quantization accuracy.
  arXiv  Detail & Related papers  (2021-09-16T10:59:33Z)
• On the Acceleration of Deep Neural Network Inference using Quantized Compressed Sensing [0.0]
  We propose a novel binary quantization function based on quantized compressed sensing (QCS) Our proposal preserves the practical benefits of standard methods, while reducing the quantization error and the resulting drop in accuracy.
  arXiv  Detail & Related papers  (2021-08-23T12:03:24Z)
• 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)
• Scalable Neural Decoder for Topological Surface Codes [0.0]
  We present a neural network based decoder for a family of stabilizer codes subject to noise and syndrome measurement errors. The key innovation is to autodecode error syndromes on small scales by shifting a preprocessing window over the underlying code. We show that such a preprocessing step allows to effectively reduce the error rate by up to two orders of magnitude in practical applications.
  arXiv  Detail & Related papers  (2021-01-18T19:02:09Z)
• 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)
• Bayesian Bits: Unifying Quantization and Pruning [73.27732135853243]
  We introduce Bayesian Bits, a practical method for joint mixed precision quantization and pruning through gradient based optimization. We experimentally validate our proposed method on several benchmark datasets and show that we can learn pruned, mixed precision networks.
  arXiv  Detail & Related papers  (2020-05-14T16:00:34Z)
• Kernel Quantization for Efficient Network Compression [59.55192551370948]
  Kernel Quantization (KQ) aims to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version without significant performance loss. Inspired by the evolution from weight pruning to filter pruning, we propose to quantize in both kernel and weight level. Experiments on the ImageNet classification task prove that KQ needs 1.05 and 1.62 bits on average in VGG and ResNet18, respectively, to represent each parameter in the convolution layer.
  arXiv  Detail & Related papers  (2020-03-11T08:00:04Z)
• Quantized Neural Network Inference with Precision Batching [4.519884877213097]
  Precision decomposes a neural network into individual bitlayers and accumulates them using fast 1-bit operations. Precision yields end-to-endups of over 8x on a GPU within a 1% error margin of the full precision baseline. Across a variety of applications, Precision yields end-to-endups of over 8x on a GPU within a 1% error margin of the full precision baseline.
  arXiv  Detail & Related papers  (2020-02-26T19:34:11Z)

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.