paper-with-me

홈 › Papers

Exploring the Performance of Pruning Methods in Neural Networks: An Empirical Study of the Lottery Ticket Hypothesis

2023-03-26 · Eirik Fladmark, Muhammad Hamza Sajjad, Laura Brinkholm Justesen

In this paper, we explore the performance of different pruning methods in the context of the lottery ticket hypothesis. We compare the performance of L1 unstructured pruning, Fisher pruning, and random pruning on different network architectures and pruning scenarios. The experiments include an evaluation of one-shot and iterative pruning, an examination of weight movement in the network during pruning, a comparison of the pruning methods on networks of varying widths, and an analysis of the performance of the methods when the network becomes very sparse. Additionally, we propose and evaluate a new method for efficient computation of Fisher pruning, known as batched Fisher pruning.

📄 PDF Abstract BibTeX arXiv:2303.15479

Code (1)

fladmark/open_lth 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models

2026-04-29 · M. K. Khalidi Siam, Md. Tausif-Ul-Islam, Md. Reshad Romim Khan, Mohammed Ali Hossain 외 arxiv

Neuron pruning is widely used to reduce the computational cost and parameter footprint of large language models, yet it remains unclear whether neurons in task-specific models contribute uniformly to task performance. In…

Mathematical ReasoningCode Generation

ITP: Instance-Aware Test Pruning for Out-of-Distribution Detection

2024-12-17 · Haonan Xu, Yang Yang

Out-of-distribution (OOD) detection is crucial for ensuring the reliable deployment of deep models in real-world scenarios. Recently, from the perspective of over-parameterization, a series of methods leveraging weight s…

Out-of-Distribution DetectionOut of Distribution (OOD) Detection

RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging

2021-09-30 · Edouard Yvinec, Arnaud Dapogny, Matthieu Cord, Kevin Bailly

Pruning Deep Neural Networks (DNNs) is a prominent field of study in the goal of inference runtime acceleration. In this paper, we introduce a novel data-free pruning protocol RED++. Only requiring a trained neural netwo…

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

2025-06-05 · Yubo Ma, Jinsong Li, Yuhang Zang, Xiaobao Wu 외

Despite the strong performance of ColPali/ColQwen2 in Visualized Document Retrieval (VDR), it encodes each page into multiple patch-level embeddings and leads to excessive memory usage. This empirical study investigates …

RetrievalToken Reduction

BWCP: Probabilistic Learning-to-Prune Channels for ConvNets via Batch Whitening

2021-05-13 · Wenqi Shao, Hang Yu, Zhaoyang Zhang, Hang Xu 외

This work presents a probabilistic channel pruning method to accelerate Convolutional Neural Networks (CNNs). Previous pruning methods often zero out unimportant channels in training in a deterministic manner, which redu…