Winograd Convolution for Deep Neural Networks: Efficient Point Selection

• URL: http://arxiv.org/abs/2201.10369v1
• Date: Tue, 25 Jan 2022 15:00:54 GMT
• Title: Winograd Convolution for Deep Neural Networks: Efficient Point Selection
• Authors: Syed Asad Alam, Andrew Anderson, Barbara Barabasz and David Gregg
• Abstract summary: We propose a novel approach to point selection using points of the form -1/c, -c, c, 1/c using the full range of real-valued numbers for c. We find that the error for different values of c forms a rough curve across the range of real-value numbers helping to localize the values of c that reduce error. We study a range of sizes for small convolutions and achieve reduction in error ranging from 2% to around 59% for both 1D and 2D convolutions.
• Score: 0.8043754868448141
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional neural networks (CNNs) have dramatically improved the accuracy of tasks such as object recognition, image segmentation and interactive speech systems. CNNs require large amounts of computing resources because ofcomputationally intensive convolution layers. Fast convolution algorithms such as Winograd convolution can greatly reduce the computational cost of these layers at a cost of poor numeric properties, such that greater savings in computation exponentially increase floating point errors. A defining feature of each Winograd convolution algorithm is a set of real-value points where polynomials are sampled. The choice of points impacts the numeric accuracy of the algorithm, but the optimal set of points for small convolutions remains unknown. Existing work considers only small integers and simple fractions as candidate points. In this work, we propose a novel approach to point selection using points of the form {-1/c , -c, c, 1/c } using the full range of real-valued numbers for c. We show that groups of this form cause cancellations in the Winograd transform matrices that reduce numeric error. We find empirically that the error for different values of c forms a rough curve across the range of real-value numbers helping to localize the values of c that reduce error and that lower errors can be achieved with non-obvious real-valued evaluation points instead of integers or simple fractions. We study a range of sizes for small convolutions and achieve reduction in error ranging from 2% to around 59% for both 1D and 2D convolution. Furthermore, we identify patterns in cases when we select a subset of our proposed points which will always lead to a lower error. Finally we implement a complete Winograd convolution layer and use it to run deep convolution neural networks on real datasets and show that our proposed points reduce error, ranging from 22% to 63%.

Related papers

• Quality Scalable Quantization Methodology for Deep Learning on Edge [0.20718016474717196]
  Deep Learning Architectures employ heavy computations and bulk of the computational energy is taken up by the convolution operations in the Convolutional Neural Networks. The proposed work is to reduce the energy consumption and size of CNN for using machine learning techniques in edge computing on ubiquitous computing devices. The experiments done on LeNet and ConvNets show an increase upto 6% of zeros and memory savings upto 82.4919% while keeping the accuracy near the state of the art.
  arXiv  Detail & Related papers  (2024-07-15T22:00:29Z)
• On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee [21.818773423324235]
  This paper focuses on two model compression techniques: low-rank approximation and weight approximation. In this paper, a holistic framework is proposed for model compression from a novel perspective of non optimization.
  arXiv  Detail & Related papers  (2023-03-13T02:14:42Z)
• Efficient Dataset Distillation Using Random Feature Approximation [109.07737733329019]
  We propose a novel algorithm that uses a random feature approximation (RFA) of the Neural Network Gaussian Process (NNGP) kernel. Our algorithm provides at least a 100-fold speedup over KIP and can run on a single GPU. Our new method, termed an RFA Distillation (RFAD), performs competitively with KIP and other dataset condensation algorithms in accuracy over a range of large-scale datasets.
  arXiv  Detail & Related papers  (2022-10-21T15:56:13Z)
• Adaptive Self-supervision Algorithms for Physics-informed Neural Networks [59.822151945132525]
  Physics-informed neural networks (PINNs) incorporate physical knowledge from the problem domain as a soft constraint on the loss function. We study the impact of the location of the collocation points on the trainability of these models. We propose a novel adaptive collocation scheme which progressively allocates more collocation points to areas where the model is making higher errors.
  arXiv  Detail & Related papers  (2022-07-08T18:17:06Z)
• Large-Margin Representation Learning for Texture Classification [67.94823375350433]
  This paper presents a novel approach combining convolutional layers (CLs) and large-margin metric learning for training supervised models on small datasets for texture classification. The experimental results on texture and histopathologic image datasets have shown that the proposed approach achieves competitive accuracy with lower computational cost and faster convergence when compared to equivalent CNNs.
  arXiv  Detail & Related papers  (2022-06-17T04:07:45Z)
• Content-Aware Convolutional Neural Networks [98.97634685964819]
  Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. We propose a Content-aware Convolution (CAC) that automatically detects the smooth windows and applies a 1x1 convolutional kernel to replace the original large kernel.
  arXiv  Detail & Related papers  (2021-06-30T03:54:35Z)
• Achieving Small Test Error in Mildly Overparameterized Neural Networks [30.664282759625948]
  We show an algorithm which finds one of these points in time. In addition, we prove that for a fully connected neural net, with an additional assumption on the data distribution, there is a time algorithm.
  arXiv  Detail & Related papers  (2021-04-24T06:47:20Z)
• Hybrid Trilinear and Bilinear Programming for Aligning Partially Overlapping Point Sets [85.71360365315128]
  In many applications, we need algorithms which can align partially overlapping point sets are invariant to the corresponding corresponding RPM algorithm. We first show that the objective is a cubic bound function. We then utilize the convex envelopes of trilinear and bilinear monomial transformations to derive its lower bound. We next develop a branch-and-bound (BnB) algorithm which only branches over the transformation variables and runs efficiently.
  arXiv  Detail & Related papers  (2021-01-19T04:24:23Z)
• Quantaized Winograd/Toom-Cook Convolution for DNNs: Beyond Canonical Polynomials Base [0.0]
  Winograd convolution algorithm is a common used method that significantly reduces time consumption. We present the application of base change technique for quantized Winograd-aware training model.
  arXiv  Detail & Related papers  (2020-04-23T11:15:27Z)
• Variance Reduction with Sparse Gradients [82.41780420431205]
  Variance reduction methods such as SVRG and SpiderBoost use a mixture of large and small batch gradients. We introduce a new sparsity operator: The random-top-k operator. Our algorithm consistently outperforms SpiderBoost on various tasks including image classification, natural language processing, and sparse matrix factorization.
  arXiv  Detail & Related papers  (2020-01-27T08:23:58Z)

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.