paper-with-me

Papers

LPZero: Language Model Zero-cost Proxy Search from Zero

2024-10-07 · Peijie Dong, Lujun Li, Xiang Liu, Zhenheng Tang, Xuebo Liu, Qiang Wang, Xiaowen Chu

In spite of the outstanding performance, Neural Architecture Search (NAS) is criticized for massive computation. Recently, Zero-shot NAS has emerged as a promising approach by exploiting Zero-cost (ZC) proxies, which markedly reduce computational demands. Despite this, existing ZC proxies heavily rely on expert knowledge and incur significant trial-and-error costs. Particularly in NLP tasks, most existing ZC proxies fail to surpass the performance of the naive baseline. To address these challenges, we introduce a novel framework, \textbf{LPZero}, which is the first to automatically design ZC proxies for various tasks, achieving higher ranking consistency than human-designed proxies. Specifically, we model the ZC proxy as a symbolic equation and incorporate a unified proxy search space that encompasses existing ZC proxies, which are composed of a predefined set of mathematical symbols. To heuristically search for the best ZC proxy, LPZero incorporates genetic programming to find the optimal symbolic composition. We propose a \textit{Rule-based Pruning Strategy (RPS),} which preemptively eliminates unpromising proxies, thereby mitigating the risk of proxy degradation. Extensive experiments on FlexiBERT, GPT-2, and LLaMA-7B demonstrate LPZero's superior ranking ability and performance on downstream tasks compared to current approaches.

📄 PDF Abstract BibTeX arXiv:2410.04808

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingNeural Architecture Search

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Weight Decay 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Auto-Prox: Training-Free Vision Transformer Architecture Search via Automatic Proxy Discovery

2023-12-14 · Zimian Wei, Lujun Li, Peijie Dong, Zheng Hui 외

The substantial success of Vision Transformer (ViT) in computer vision tasks is largely attributed to the architecture design. This underscores the necessity of efficient architecture search for designing better ViTs aut…

ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxies

2021-10-20 · Yu Shen, Yang Li, Jian Zheng, Wentao Zhang 외

Designing neural architectures requires immense manual efforts. This has promoted the development of neural architecture search (NAS) to automate the design. While previous NAS methods achieve promising results but run s…

Bayesian OptimizationNeural Architecture Search

Zero-Cost Proxies for Lightweight NAS

2021-01-20 · ICLR 2021 1 · Mohamed S. Abdelfattah, Abhinav Mehrotra, Łukasz Dudziak, Nicholas D. Lane

Neural Architecture Search (NAS) is quickly becoming the standard methodology to design neural network models. However, NAS is typically compute-intensive because multiple models need to be evaluated before choosing the …

Neural Architecture Search

Extensible Proxy for Efficient NAS

2022-10-17 · Yuhong Li, Jiajie Li, Cong Han, Pan Li 외

Neural Architecture Search (NAS) has become a de facto approach in the recent trend of AutoML to design deep neural networks (DNNs). Efficient or near-zero-cost NAS proxies are further proposed to address the demanding c…

AutoMLNeural Architecture Search

ZeroLM: Data-Free Transformer Architecture Search for Language Models

2025-03-24 · Zhen-Song Chen, Hong-Wei Ding, Xian-Jia Wang, Witold Pedrycz

Neural architecture search (NAS) provides a systematic framework for automating the design of neural network architectures, yet its widespread adoption is hindered by prohibitive computational requirements. Existing zero…

Computational EfficiencyNeural Architecture Search