paper-with-me

Papers

A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods

2020-04-12 · Tianyun Zhang, Xiaolong Ma, Zheng Zhan, Shanglin Zhou, Minghai Qin, Fei Sun, Yen-Kuang Chen, Caiwen Ding, Makan Fardad, Yanzhi Wang

To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i.e., static regularization-based pruning and dynamic regularization-based pruning. However, the former method currently suffers either complex workloads or accuracy degradation, while the latter one takes a long time to tune the parameters to achieve the desired pruning rate without accuracy loss. In this paper, we propose a unified DNN weight pruning framework with dynamically updated regularization terms bounded by the designated constraint, which can generate both non-structured sparsity and different kinds of structured sparsity. We also extend our method to an integrated framework for the combination of different DNN compression tasks.

📄 PDF Abstract BibTeX arXiv:2004.05531

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

UniRain: Unified Image Deraining with RAG-based Dataset Distillation and Multi-objective Reweighted Optimization

2026-03-04 · Qianfeng Yang, Qiyuan Guan, Xiang Chen, Jiyu Jin 외 arxiv

Despite significant progress has been made in image deraining, we note that most existing methods are often developed for only specific types of rain degradation and fail to generalize across diverse real-world rainy sce…

Comparison of several reweighted l1-algorithms for solving cardinality minimization problems

2013-04-24 · Mohammad Javad Abdi

Reweighted l1-algorithms have attracted a lot of attention in the field of applied mathematics. A unified framework of such algorithms has been recently proposed by Zhao and Li. In this paper we construct a few new examp…

A Deep Recurrent Neural Network via Unfolding Reweighted l1-l1 Minimization

2019-09-25 · Huynh Van Luong, Duy Hung Le, Nikos Deligiannis

Deep unfolding methods design deep neural networks as learned variations of optimization methods. These networks have been shown to achieve faster convergence and higher accuracy than the original optimization methods. I…

Nonconvex and Nonsmooth Sparse Optimization via Adaptively Iterative Reweighted Methods

2018-10-24 · Hao Wang, Fan Zhang, Yuanming Shi, Yaohua Hu

We propose a general formulation of nonconvex and nonsmooth sparse optimization problems with convex set constraint, which can take into account most existing types of nonconvex sparsity-inducing terms, bringing strong a…

Interpretable Deep Recurrent Neural Networks via Unfolding Reweighted $\ell_1$-$\ell_1$ Minimization: Architecture Design and Generalization Analysis

2020-03-18 · Huynh Van Luong, Boris Joukovsky, Nikos Deligiannis

Deep unfolding methods---for example, the learned iterative shrinkage thresholding algorithm (LISTA)---design deep neural networks as learned variations of optimization methods. These networks have been shown to achieve …