paper-with-me

Papers

Prune and Replace NAS

2019-06-18 · Kevin Alexander Laube, Andreas Zell

While recent NAS algorithms are thousands of times faster than the pioneering works, it is often overlooked that they use fewer candidate operations, resulting in a significantly smaller search space. We present PR-DARTS, a NAS algorithm that discovers strong network configurations in a much larger search space and a single day. A small candidate operation pool is used, from which candidates are progressively pruned and replaced with better performing ones. Experiments on CIFAR-10 and CIFAR-100 achieve 2.51% and 15.53% test error, respectively, despite searching in a space where each cell has 150 times as many possible configurations than in the DARTS baseline. Code is available at https://github.com/cogsys-tuebingen/prdarts

📄 PDF Abstract BibTeX arXiv:1906.07528

Code (1)

cogsys-tuebingen/prdarts 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

DARTS Differentiable Architecture Search (DART) is a method for efficient architecture search. The search space is made continuous so that the architecture can be optimized with…

Similar Papers 제목 키워드 기반

FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing

2025-01-24 · James Seale Smith, Chi-Heng Lin, Shikhar Tuli, Haris Jeelani 외

The rapid proliferation of large language models (LLMs) in natural language processing (NLP) has created a critical need for techniques that enable efficient deployment on memory-constrained devices without compromising …

Streamlining Redundant Layers to Compress Large Language Models

2024-03-28 · Xiaodong Chen, Yuxuan Hu, Jing Zhang, Yanling Wang 외

This paper introduces LLM-Streamline, a pioneer work on layer pruning for large language models (LLMs). It is based on the observation that different layers have varying impacts on hidden states, enabling the identificat…

Model Compression

PrunePath: Towards Highly Structured Sparse Language Models

2026-05-27 · Zhexuan Gu, Zixun Fu, Yancheng Yuan arxiv

Feed-forward networks (FFNs) dominate the parameter count and computation of modern language models, yet existing pruning methods often struggle to convert sparsity into hardware-friendly inference efficiency gains. We i…

Reconstructing Pruned Filters using Cheap Spatial Transformations

2021-10-25 · Roy Miles, Krystian Mikolajczyk

We present an efficient alternative to the convolutional layer using cheap spatial transformations. This construction exploits an inherent spatial redundancy of the learned convolutional filters to enable a much greater …

Feature CompressionKnowledge DistillationModel Compression

Pruning Neural Networks at Initialization: Why are We Missing the Mark?

2020-09-18 · ICLR 2021 1 · Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy, Michael Carbin

Recent work has explored the possibility of pruning neural networks at initialization. We assess proposals for doing so: SNIP (Lee et al., 2019), GraSP (Wang et al., 2020), SynFlow (Tanaka et al., 2020), and magnitude pr…