Numerical Pruning for Efficient Autoregressive Models

• URL: http://arxiv.org/abs/2412.12441v1
• Date: Tue, 17 Dec 2024 01:09:23 GMT
• Title: Numerical Pruning for Efficient Autoregressive Models
• Authors: Xuan Shen, Zhao Song, Yufa Zhou, Bo Chen, Jing Liu, Ruiyi Zhang, Ryan A. Rossi, Hao Tan, Tong Yu, Xiang Chen, Yufan Zhou, Tong Sun, Pu Zhao, Yanzhi Wang, Jiuxiang Gu,
• Abstract summary: This paper focuses on compressing decoder-only transformer-based autoregressive models through structural weight pruning. Specifically, we propose a training-free pruning method that calculates a numerical score with Newton's method for the Attention and modules, respectively. To verify the effectiveness of our method, we provide both theoretical support and extensive experiments.
• Score: 87.56342118369123
• License:
• Abstract: Transformers have emerged as the leading architecture in deep learning, proving to be versatile and highly effective across diverse domains beyond language and image processing. However, their impressive performance often incurs high computational costs due to their substantial model size. This paper focuses on compressing decoder-only transformer-based autoregressive models through structural weight pruning to improve the model efficiency while preserving performance for both language and image generation tasks. Specifically, we propose a training-free pruning method that calculates a numerical score with Newton's method for the Attention and MLP modules, respectively. Besides, we further propose another compensation algorithm to recover the pruned model for better performance. To verify the effectiveness of our method, we provide both theoretical support and extensive experiments. Our experiments show that our method achieves state-of-the-art performance with reduced memory usage and faster generation speeds on GPUs.

Related papers

• Efficient Transformer for High Resolution Image Motion Deblurring [0.0]
  This paper presents a comprehensive study and improvement of the Restormer architecture for high-resolution image motion deblurring. We introduce architectural modifications that reduce model complexity by 18.4% while maintaining or improving performance through optimized attention mechanisms. Our results suggest that thoughtful architectural simplification combined with enhanced training strategies can yield more efficient yet equally capable models for motion deblurring tasks.
  arXiv  Detail & Related papers  (2025-01-30T14:58:33Z)
• Distillation of Diffusion Features for Semantic Correspondence [23.54555663670558]
  We propose a novel knowledge distillation technique to overcome the problem of reduced efficiency. We show how to use two large vision foundation models and distill the capabilities of these complementary models into one smaller model that maintains high accuracy at reduced computational cost. Our empirical results demonstrate that our distilled model with 3D data augmentation achieves performance superior to current state-of-the-art methods while significantly reducing computational load and enhancing practicality for real-world applications, such as semantic video correspondence.
  arXiv  Detail & Related papers  (2024-12-04T17:55:33Z)
• Efficient Degradation-aware Any Image Restoration [83.92870105933679]
  We propose textitDaAIR, an efficient All-in-One image restorer employing a Degradation-aware Learner (DaLe) in the low-rank regime. By dynamically allocating model capacity to input degradations, we realize an efficient restorer integrating holistic and specific learning.
  arXiv  Detail & Related papers  (2024-05-24T11:53:27Z)
• Majority Kernels: An Approach to Leverage Big Model Dynamics for Efficient Small Model Training [32.154166415680066]
  Methods like distillation, compression or quantization help leverage the highly performant large models to induce smaller performant ones. This paper explores the hypothesis that a single training run can simultaneously train a larger model for performance and derive a smaller model for deployment.
  arXiv  Detail & Related papers  (2024-02-07T17:07:41Z)
• A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization [54.113083217869516]
  In this work, we first explore the computational redundancy part of the network. We then prune the redundancy blocks of the model and maintain the network performance. Thirdly, we propose a global-regional interactive (GRI) attention to speed up the computationally intensive attention part.
  arXiv  Detail & Related papers  (2023-12-24T15:37:47Z)
• Towards Compute-Optimal Transfer Learning [82.88829463290041]
  We argue that zero-shot structured pruning of pretrained models allows them to increase compute efficiency with minimal reduction in performance. Our results show that pruning convolutional filters of pretrained models can lead to more than 20% performance improvement in low computational regimes.
  arXiv  Detail & Related papers  (2023-04-25T21:49:09Z)
• Top-KAST: Top-K Always Sparse Training [50.05611544535801]
  We propose Top-KAST, a method that preserves constant sparsity throughout training. We show that it performs comparably to or better than previous works when training models on the established ImageNet benchmark. In addition to our ImageNet results, we also demonstrate our approach in the domain of language modeling.
  arXiv  Detail & Related papers  (2021-06-07T11:13:05Z)
• Towards Practical Lipreading with Distilled and Efficient Models [57.41253104365274]
  Lipreading has witnessed a lot of progress due to the resurgence of neural networks. Recent works have placed emphasis on aspects such as improving performance by finding the optimal architecture or improving generalization. There is still a significant gap between the current methodologies and the requirements for an effective deployment of lipreading in practical scenarios. We propose a series of innovations that significantly bridge that gap: first, we raise the state-of-the-art performance by a wide margin on LRW and LRW-1000 to 88.5% and 46.6%, respectively using self-distillation.
  arXiv  Detail & Related papers  (2020-07-13T16:56:27Z)

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.