Scalable iterative pruning of large language and vision models using block coordinate descent

• URL: http://arxiv.org/abs/2411.17796v1
• Date: Tue, 26 Nov 2024 17:54:02 GMT
• Title: Scalable iterative pruning of large language and vision models using block coordinate descent
• Authors: Gili Rosenberg, J. Kyle Brubaker, Martin J. A. Schuetz, Elton Yechao Zhu, Serdar Kadıoğlu, Sima E. Borujeni, Helmut G. Katzgraber,
• Abstract summary: Pruning neural networks, which involves removing a fraction of their weights, can often maintain high accuracy while significantly reducing model complexity, at least up to a certain limit. We present a neural network pruning technique that builds upon the Combinatorial Brain Surgeon, but solves an optimization problem over a subset of the network weights in an iterative, block-wise manner.
• Score: 0.31410859223862103
• License:
• Abstract: Pruning neural networks, which involves removing a fraction of their weights, can often maintain high accuracy while significantly reducing model complexity, at least up to a certain limit. We present a neural network pruning technique that builds upon the Combinatorial Brain Surgeon, but solves an optimization problem over a subset of the network weights in an iterative, block-wise manner using block coordinate descent. The iterative, block-based nature of this pruning technique, which we dub ``iterative Combinatorial Brain Surgeon'' (iCBS) allows for scalability to very large models, including large language models (LLMs), that may not be feasible with a one-shot combinatorial optimization approach. When applied to large models like Mistral and DeiT, iCBS achieves higher performance metrics at the same density levels compared to existing pruning methods such as Wanda. This demonstrates the effectiveness of this iterative, block-wise pruning method in compressing and optimizing the performance of large deep learning models, even while optimizing over only a small fraction of the weights. Moreover, our approach allows for a quality-time (or cost) tradeoff that is not available when using a one-shot pruning technique alone. The block-wise formulation of the optimization problem enables the use of hardware accelerators, potentially offsetting the increased computational costs compared to one-shot pruning methods like Wanda. In particular, the optimization problem solved for each block is quantum-amenable in that it could, in principle, be solved by a quantum computer.

Related papers

• Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization [0.0]
  We present Double Sparse Factorization (DSF), where we factorize each weight matrix into two sparse matrices. Our method achieves state-of-the-art results, enabling unprecedented sparsification of neural networks.
  arXiv  Detail & Related papers  (2024-09-27T15:48:39Z)
• Self-Improved Learning for Scalable Neural Combinatorial Optimization [15.842155380912002]
  This work proposes a novel Self-Improved Learning (SIL) method for better scalability of neural optimization. We develop an efficient self-improved mechanism that enables direct model training on large-scale problem instances without any labeled data. In addition, we design a linear attention complexity mechanism for the computation model to efficiently handle large-scale problem instances with low overhead.
  arXiv  Detail & Related papers  (2024-03-28T16:46:53Z)
• SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization [22.888876901031043]
  Neural network pruning is a key technique towards engineering large yet scalable, interpretable, generalizable models. We show how many existing differentiable pruning techniques can be understood as non regularization for group sparse optimization. We propose SequentialAttention++, which advances state the art in large-scale neural network block-wise pruning tasks on the ImageNet and Criteo datasets.
  arXiv  Detail & Related papers  (2024-02-27T21:42:18Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• 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)
• Symmetric Tensor Networks for Generative Modeling and Constrained Combinatorial Optimization [72.41480594026815]
  Constrained optimization problems abound in industry, from portfolio optimization to logistics. One of the major roadblocks in solving these problems is the presence of non-trivial hard constraints which limit the valid search space. In this work, we encode arbitrary integer-valued equality constraints of the form Ax=b, directly into U(1) symmetric networks (TNs) and leverage their applicability as quantum-inspired generative models.
  arXiv  Detail & Related papers  (2022-11-16T18:59:54Z)
• Effective Invertible Arbitrary Image Rescaling [77.46732646918936]
  Invertible Neural Networks (INN) are able to increase upscaling accuracy significantly by optimizing the downscaling and upscaling cycle jointly. A simple and effective invertible arbitrary rescaling network (IARN) is proposed to achieve arbitrary image rescaling by training only one model in this work. It is shown to achieve a state-of-the-art (SOTA) performance in bidirectional arbitrary rescaling without compromising perceptual quality in LR outputs.
  arXiv  Detail & Related papers  (2022-09-26T22:22:30Z)
• DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting [70.62923754433461]
  Analyzing the worst-case performance of deep neural networks against input perturbations amounts to solving a large-scale non- optimization problem. We propose a novel method that can directly solve a convex relaxation of the problem to high accuracy, by splitting it into smaller subproblems that often have analytical solutions.
  arXiv  Detail & Related papers  (2021-06-16T20:43:49Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• Efficient and Sparse Neural Networks by Pruning Weights in a Multiobjective Learning Approach [0.0]
  We propose a multiobjective perspective on the training of neural networks by treating its prediction accuracy and the network complexity as two individual objective functions. Preliminary numerical results on exemplary convolutional neural networks confirm that large reductions in the complexity of neural networks with neglibile loss of accuracy are possible.
  arXiv  Detail & Related papers  (2020-08-31T13:28:03Z)
• Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [83.98774574197613]
  We take one of the simplest inference methods, a truncated max-product Belief propagation, and add what is necessary to make it a proper component of a deep learning model. This BP-Layer can be used as the final or an intermediate block in convolutional neural networks (CNNs) The model is applicable to a range of dense prediction problems, is well-trainable and provides parameter-efficient and robust solutions in stereo, optical flow and semantic segmentation.
  arXiv  Detail & Related papers  (2020-03-13T13:11:35Z)

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.