all AI news
LoRA Dropout as a Sparsity Regularizer for Overfitting Control
April 16, 2024, 4:42 a.m. | Yang Lin, Xinyu Ma, Xu Chu, Yujie Jin, Zhibang Yang, Yasha Wang, Hong Mei
cs.LG updates on arXiv.org arxiv.org
Abstract: Parameter-efficient fine-tuning methods, represented by LoRA, play an essential role in adapting large-scale pre-trained models to downstream tasks. However, fine-tuning LoRA-series models also faces the risk of overfitting on the training dataset, and yet there's still a lack of theoretical guidance and practical mechanism to control overfitting on LoRA-based PEFT methods. In this paper, we propose a LoRA Dropout mechanism for the LoRA-based methods by introducing random noises to the learnable low-rank matrices and increasing …
abstract arxiv control cs.ai cs.lg dataset dropout fine-tuning guidance however lora overfitting practical pre-trained models risk role scale series sparsity tasks training type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Sr. VBI Developer II
@ Atos | Texas, US, 75093
Wealth Management - Data Analytics Intern/Co-op Fall 2024
@ Scotiabank | Toronto, ON, CA