Exploiting Elasticity in Tensor Ranks for Compressing Neural Networks

• URL: http://arxiv.org/abs/2105.04218v1
• Date: Mon, 10 May 2021 09:26:47 GMT
• Title: Exploiting Elasticity in Tensor Ranks for Compressing Neural Networks
• Authors: Jie Ran, Rui Lin, Hayden K.H. So, Graziano Chesi, Ngai Wong
• Abstract summary: We exploit a new dimension of elasticity along the input-output channels in a convolutional neural network (CNN) A novel nuclear-norm rank minimization factorization (NRMF) approach is proposed to search for the reduced tensor ranks during training. Experiments show the superiority of NRMF over the previous non-elastic variational Bayesian matrix factorization scheme.
• Score: 8.180947044673639
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Elasticities in depth, width, kernel size and resolution have been explored in compressing deep neural networks (DNNs). Recognizing that the kernels in a convolutional neural network (CNN) are 4-way tensors, we further exploit a new elasticity dimension along the input-output channels. Specifically, a novel nuclear-norm rank minimization factorization (NRMF) approach is proposed to dynamically and globally search for the reduced tensor ranks during training. Correlation between tensor ranks across multiple layers is revealed, and a graceful tradeoff between model size and accuracy is obtained. Experiments then show the superiority of NRMF over the previous non-elastic variational Bayesian matrix factorization (VBMF) scheme.

Related papers

• Novel Kernel Models and Exact Representor Theory for Neural Networks Beyond the Over-Parameterized Regime [52.00917519626559]
  This paper presents two models of neural-networks and their training applicable to neural networks of arbitrary width, depth and topology. We also present an exact novel representor theory for layer-wise neural network training with unregularized gradient descent in terms of a local-extrinsic neural kernel (LeNK) This representor theory gives insight into the role of higher-order statistics in neural network training and the effect of kernel evolution in neural-network kernel models.
  arXiv  Detail & Related papers  (2024-05-24T06:30:36Z)
• Speed Limits for Deep Learning [67.69149326107103]
  Recent advancement in thermodynamics allows bounding the speed at which one can go from the initial weight distribution to the final distribution of the fully trained network. We provide analytical expressions for these speed limits for linear and linearizable neural networks. Remarkably, given some plausible scaling assumptions on the NTK spectra and spectral decomposition of the labels -- learning is optimal in a scaling sense.
  arXiv  Detail & Related papers  (2023-07-27T06:59:46Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• Variational Tensor Neural Networks for Deep Learning [0.0]
  We propose an integration of tensor networks (TN) into deep neural networks (NNs) This in turn, results in a scalable tensor neural network (TNN) architecture capable of efficient training over a large parameter space. We validate the accuracy and efficiency of our method by designing TNN models and providing benchmark results for linear and non-linear regressions, data classification and image recognition on MNIST handwritten digits.
  arXiv  Detail & Related papers  (2022-11-26T20:24:36Z)
• Tensor-based framework for training flexible neural networks [9.176056742068813]
  We propose a new learning algorithm which solves a constrained coupled matrix-tensor factorization (CMTF) problem. The proposed algorithm can handle different bases decomposition. The goal of this method is to compress large pretrained NN models, by replacing tensorworks, em i.e., one or multiple layers of the original network, by a new flexible layer.
  arXiv  Detail & Related papers  (2021-06-25T10:26:48Z)
• Tensor-Train Networks for Learning Predictive Modeling of Multidimensional Data [0.0]
  A promising strategy is based on tensor networks, which have been very successful in physical and chemical applications. We show that the weights of a multidimensional regression model can be learned by means of tensor networks with the aim of performing a powerful compact representation. An algorithm based on alternating least squares has been proposed for approximating the weights in TT-format with a reduction of computational power.
  arXiv  Detail & Related papers  (2021-01-22T16:14:38Z)
• A Fully Tensorized Recurrent Neural Network [48.50376453324581]
  We introduce a "fully tensorized" RNN architecture which jointly encodes the separate weight matrices within each recurrent cell. This approach reduces model size by several orders of magnitude, while still maintaining similar or better performance compared to standard RNNs.
  arXiv  Detail & Related papers  (2020-10-08T18:24:12Z)
• Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network [19.717842489217684]
  This paper is the first study on degeneracy in the tensor decomposition of convolutional kernels. We present a novel method, which can stabilize the low-rank approximation of convolutional kernels and ensure efficient compression. We evaluate our approach on popular CNN architectures for image classification and show that our method results in much lower accuracy degradation and provides consistent performance.
  arXiv  Detail & Related papers  (2020-08-12T17:10:12Z)
• Finite Versus Infinite Neural Networks: an Empirical Study [69.07049353209463]
  kernel methods outperform fully-connected finite-width networks. Centered and ensembled finite networks have reduced posterior variance. Weight decay and the use of a large learning rate break the correspondence between finite and infinite networks.
  arXiv  Detail & Related papers  (2020-07-31T01:57:47Z)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)

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.