Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification

• URL: http://arxiv.org/abs/2004.09031v1
• Date: Mon, 20 Apr 2020 02:40:43 GMT
• Title: Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
• Authors: Huanrui Yang, Minxue Tang, Wei Wen, Feng Yan, Daniel Hu, Ang Li, Hai Li, Yiran Chen
• Abstract summary: We propose SVD training, the first method to explicitly achieve low-rank DNNs during training without applying SVD on every step. We empirically show that SVD training can significantly reduce the rank of DNN layers and achieve higher reduction on computation load under the same accuracy.
• Score: 53.50708351813565
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern deep neural networks (DNNs) often require high memory consumption and large computational loads. In order to deploy DNN algorithms efficiently on edge or mobile devices, a series of DNN compression algorithms have been explored, including factorization methods. Factorization methods approximate the weight matrix of a DNN layer with the multiplication of two or multiple low-rank matrices. However, it is hard to measure the ranks of DNN layers during the training process. Previous works mainly induce low-rank through implicit approximations or via costly singular value decomposition (SVD) process on every training step. The former approach usually induces a high accuracy loss while the latter has a low efficiency. In this work, we propose SVD training, the first method to explicitly achieve low-rank DNNs during training without applying SVD on every step. SVD training first decomposes each layer into the form of its full-rank SVD, then performs training directly on the decomposed weights. We add orthogonality regularization to the singular vectors, which ensure the valid form of SVD and avoid gradient vanishing/exploding. Low-rank is encouraged by applying sparsity-inducing regularizers on the singular values of each layer. Singular value pruning is applied at the end to explicitly reach a low-rank model. We empirically show that SVD training can significantly reduce the rank of DNN layers and achieve higher reduction on computation load under the same accuracy, comparing to not only previous factorization methods but also state-of-the-art filter pruning methods.

Related papers

• Maestro: Uncovering Low-Rank Structures via Trainable Decomposition [15.254107731735553]
  Deep Neural Networks (DNNs) have been a large driver for AI breakthroughs in recent years. They have been getting increasingly large as they become more accurate and safe. This means that their training becomes increasingly costly and time-consuming. We propose Maestro, a framework for trainable low-rank layers.
  arXiv  Detail & Related papers  (2023-08-28T23:08:15Z)
• Layer-wise Adaptive Step-Sizes for Stochastic First-Order Methods for Deep Learning [8.173034693197351]
  We propose a new per-layer adaptive step-size procedure for first-order optimization methods in deep learning. The proposed approach exploits the layer-wise curvature information contained in the diagonal blocks of the Hessian in deep neural networks (DNNs) to compute adaptive step-sizes (i.e., LRs) for each layer. Numerical experiments show that SGD with momentum and AdamW combined with the proposed per-layer step-sizes are able to choose effective LR schedules.
  arXiv  Detail & Related papers  (2023-05-23T04:12:55Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Variational Sparse Coding with Learned Thresholding [6.737133300781134]
  We propose a new approach to variational sparse coding that allows us to learn sparse distributions by thresholding samples. We first evaluate and analyze our method by training a linear generator, showing that it has superior performance, statistical efficiency, and gradient estimation.
  arXiv  Detail & Related papers  (2022-05-07T14:49:50Z)
• DNN Training Acceleration via Exploring GPGPU Friendly Sparsity [16.406482603838157]
  We propose the Approximate Random Dropout that replaces the conventional random dropout of neurons and synapses with a regular and online generated row-based or tile-based dropout patterns. We then develop a SGD-based Search Algorithm that produces the distribution of row-based or tile-based dropout patterns to compensate for the potential accuracy loss. We also propose the sensitivity-aware dropout method to dynamically drop the input feature maps based on their sensitivity so as to achieve greater forward and backward training acceleration.
  arXiv  Detail & Related papers  (2022-03-11T01:32:03Z)
• AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks [78.62086125399831]
  We present a general approach called Alternating Compressed/DeCompressed (AC/DC) training of deep neural networks (DNNs) AC/DC outperforms existing sparse training methods in accuracy at similar computational budgets. An important property of AC/DC is that it allows co-training of dense and sparse models, yielding accurate sparse-dense model pairs at the end of the training process.
  arXiv  Detail & Related papers  (2021-06-23T13:23:00Z)
• Effective Model Sparsification by Scheduled Grow-and-Prune Methods [73.03533268740605]
  We propose a novel scheduled grow-and-prune (GaP) methodology without pre-training the dense models. Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks.
  arXiv  Detail & Related papers  (2021-06-18T01:03:13Z)
• Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling? [59.820507600960745]
  We propose a new GCP meta-layer that uses SVD in the forward pass, and Pad'e Approximants in the backward propagation to compute the gradients. The proposed meta-layer has been integrated into different CNN models and achieves state-of-the-art performances on both large-scale and fine-grained datasets.
  arXiv  Detail & Related papers  (2021-05-06T08:03:45Z)
• Gradient Centralization: A New Optimization Technique for Deep Neural Networks [74.935141515523]
  gradient centralization (GC) operates directly on gradients by centralizing the gradient vectors to have zero mean. GC can be viewed as a projected gradient descent method with a constrained loss function. GC is very simple to implement and can be easily embedded into existing gradient based DNNs with only one line of code.
  arXiv  Detail & Related papers  (2020-04-03T10:25:00Z)

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.