paper-with-me

Papers

Network Pruning Spaces

2023-04-19 · Xuanyu He, Yu-I Yang, Ran Song, Jiachen Pu, Conggang Hu, Feijun Jiang, Wei zhang, Huanghao Ding

Network pruning techniques, including weight pruning and filter pruning, reveal that most state-of-the-art neural networks can be accelerated without a significant performance drop. This work focuses on filter pruning which enables accelerated inference with any off-the-shelf deep learning library and hardware. We propose the concept of \emph{network pruning spaces} that parametrize populations of subnetwork architectures. Based on this concept, we explore the structure aspect of subnetworks that result in minimal loss of accuracy in different pruning regimes and arrive at a series of observations by comparing subnetwork distributions. We conjecture through empirical studies that there exists an optimal FLOPs-to-parameter-bucket ratio related to the design of original network in a pruning regime. Statistically, the structure of a winning subnetwork guarantees an approximately optimal ratio in this regime. Upon our conjectures, we further refine the initial pruning space to reduce the cost of searching a good subnetwork architecture. Our experimental results on ImageNet show that the subnetwork we found is superior to those from the state-of-the-art pruning methods under comparable FLOPs.

📄 PDF Abstract BibTeX arXiv:2304.09453

Code (0)

등록된 구현이 없습니다.

Tasks

Network Pruning

Methods 이 논문이 사용한 방법론

Library 설명 없음
Pruning 설명 없음

Similar Papers 제목 키워드 기반

Demystifying When Pruning Works via Representation Hierarchies

2026-03-25 · Shwai He, Guoheng Sun, Haichao Zhang, Yun Fu 외 arxiv

Network pruning, which removes less important parameters or architectures, is often expected to improve efficiency while preserving performance. However, this expectation does not consistently hold across language tasks:…

Network Pruning

Pruning Algorithms for Low-Dimensional Non-metric k-NN Search: A Case Study

2019-10-08 · Leonid Boytsov, Eric Nyberg

We focus on low-dimensional non-metric search, where tree-based approaches permit efficient and accurate retrieval while having short indexing time. These methods rely on space partitioning and require a pruning rule to …

Retrieval

Bayesian Optimization with Clustering and Rollback for CNN Auto Pruning

2021-09-22 · Hanwei Fan, Jiandong Mu, Wei zhang

Pruning is an effective technique for convolutional neural networks (CNNs) model compression, but it is difficult to find the optimal pruning policy due to the large design space. To improve the usability of pruning, man…

Bayesian OptimizationClusteringModel Compression

Structured Pruning for Deep Convolutional Neural Networks: A survey

2023-03-01 · Yang He, Lingao Xiao

The remarkable performance of deep Convolutional neural networks (CNNs) is generally attributed to their deeper and wider architectures, which can come with significant computational costs. Pruning neural networks has th…

Network PruningNeural Architecture SearchSurvey

Layer-Adaptive State Pruning for Deep State Space Models

2024-11-05 · Minseon Gwak, Seongrok Moon, Joohwan Ko, PooGyeon Park

Due to the lack of state dimension optimization methods, deep state space models (SSMs) have sacrificed model capacity, training search space, or stability to alleviate computational costs caused by high state dimensions…

State Space Models