Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior

• URL: http://arxiv.org/abs/2411.00969v1
• Date: Fri, 01 Nov 2024 18:39:38 GMT
• Title: Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior
• Authors: Mingxuan Zhang, Yan Sun, Faming Liang,
• Abstract summary: We introduce a new magnitude-based pruning algorithm called mixture Gaussian prior pruning. It aims to retain the model's expressive capability. We provide a theoretical justification for the consistency of the sparse transformer.
• Score: 9.878774148693575
• License:
• Abstract: Large pretrained transformer models have revolutionized modern AI applications with their state-of-the-art performance in natural language processing (NLP). However, their substantial parameter count poses challenges for real-world deployment. To address this, researchers often reduce model size by pruning parameters based on their magnitude or sensitivity. Previous research has demonstrated the limitations of magnitude pruning, especially in the context of transfer learning for modern NLP tasks. In this paper, we introduce a new magnitude-based pruning algorithm called mixture Gaussian prior pruning (MGPP), which employs a mixture Gaussian prior for regularization. MGPP prunes non-expressive weights under the guidance of the mixture Gaussian prior, aiming to retain the model's expressive capability. Extensive evaluations across various NLP tasks, including natural language understanding, question answering, and natural language generation, demonstrate the superiority of MGPP over existing pruning methods, particularly in high sparsity settings. Additionally, we provide a theoretical justification for the consistency of the sparse transformer, shedding light on the effectiveness of the proposed pruning method.

Related papers

• SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values [12.137869917556415]
  Large pre-trained models (LPMs) have demonstrated exceptional performance in diverse natural language processing and computer vision tasks. fully fine-tuning these models poses substantial memory challenges, particularly in resource-constrained environments. We propose SVFit, a novel PEFT approach that leverages singular value decomposition (SVD) to low-rank matrices using critical singular values as trainable parameters.
  arXiv  Detail & Related papers  (2024-09-09T08:44:53Z)
• GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs [51.02233412547456]
  We introduce a novel PEFT method, called Gaussian noise Injected Fine Tuning of Salient Weights (GIFT-SW) Our method updates only salient columns, while injecting Gaussian noise into non-salient ones. Experiments with LLaMA models demonstrate that GIFT-SW outperforms full fine-tuning and modern PEFT methods under the same computational budget.
  arXiv  Detail & Related papers  (2024-08-27T14:41:14Z)
• Minimizing Energy Costs in Deep Learning Model Training: The Gaussian Sampling Approach [11.878350833222711]
  We propose a method called em GradSamp for sampling gradient updates from a Gaussian distribution. em GradSamp not only streamlines gradient but also enables skipping entire epochs, thereby enhancing overall efficiency. We rigorously validate our hypothesis across a diverse set of standard and non-standard CNN and transformer-based models.
  arXiv  Detail & Related papers  (2024-06-11T15:01:20Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models [52.09865918265002]
  We propose a novel quantize before fine-tuning'' framework, PreQuant. PreQuant is compatible with various quantization strategies, with outlier-aware fine-tuning incorporated to correct the induced quantization error. We demonstrate the effectiveness of PreQuant on the GLUE benchmark using BERT, RoBERTa, and T5.
  arXiv  Detail & Related papers  (2023-05-30T08:41:33Z)
• Pruning Pre-trained Language Models with Principled Importance and Self-regularization [18.088550230146247]
  Iterative pruning is one of the most effective compression methods for pre-trained language models. We propose a self-regularization scheme where model prediction is regularized by the latest checkpoint with increasing sparsity throughout pruning. Our experiments on natural language understanding, question-answering, named entity recognition, and data-to-text generation with various Transformer-based PLMs show the effectiveness of the approach at various sparsity levels.
  arXiv  Detail & Related papers  (2023-05-21T08:15:12Z)
• AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning [143.23123791557245]
  Fine-tuning large pre-trained language models on downstream tasks has become an important paradigm in NLP. We propose AdaLoRA, which adaptively allocates the parameter budget among weight matrices according to their importance score. We conduct extensive experiments with several pre-trained models on natural language processing, question answering, and natural language generation to validate the effectiveness of AdaLoRA.
  arXiv  Detail & Related papers  (2023-03-18T22:36:25Z)
• Scalable Gaussian Process Hyperparameter Optimization via Coverage Regularization [0.0]
  We present a novel algorithm which estimates the smoothness and length-scale parameters in the Matern kernel in order to improve robustness of the resulting prediction uncertainties. We achieve improved UQ over leave-one-out likelihood while maintaining a high degree of scalability as demonstrated in numerical experiments.
  arXiv  Detail & Related papers  (2022-09-22T19:23:37Z)
• Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data [66.11139091362078]
  We provide the first model selection results on large pretrained Transformers from Huggingface using generalization metrics. Despite their niche status, we find that metrics derived from the heavy-tail (HT) perspective are particularly useful in NLP tasks.
  arXiv  Detail & Related papers  (2022-02-06T20:07:35Z)
• Disentangling Generative Factors of Physical Fields Using Variational Autoencoders [0.0]
  This work explores the use of variational autoencoders (VAEs) for non-linear dimension reduction. A disentangled decomposition is interpretable and can be transferred to a variety of tasks including generative modeling.
  arXiv  Detail & Related papers  (2021-09-15T16:02:43Z)
• Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization [89.7882166459412]
  gradient noise (SGN) acts as implicit regularization for deep learning. Some works attempted to artificially simulate SGN by injecting random noise to improve deep learning. For simulating SGN at low computational costs and without changing the learning rate or batch size, we propose the Positive-Negative Momentum (PNM) approach.
  arXiv  Detail & Related papers  (2021-03-31T16:08:06Z)

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.