.png){kind=icon}
返回
Population-Based Hyperparameter Tuning With Multitask Collaboration
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2021.3130896.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Population-based optimization methods are widely used for hyperparameter (HP) tuning for a given specific task. In this work, we propose the population-based hyperparameter tuning with multitask collaboration (PHTMC), which is a general multitask collaborative framework with parallel and sequential phases for population-based HP tuning methods. In the parallel HP tuning phase, a shared population for all tasks is kept and the intertask relatedness is considered to both yield a better generalization ability and avoid data bias to a single task. In the sequential HP tuning phase, a surrogate model is built for each new-added task so that the metainformation from the existing tasks can be extracted and used to help the initialization for the new task. Experimental results show significant improvements in generalization abilities yielded by neural networks trained using the PHTMC and better performances achieved by multitask metalearning. Moreover, a visualization of the solution distribution and the autoencoder's reconstruction of both the PHTMC and a single-task population-based HP tuning method is compared to analyze the property with the multitask collaboration.
Keyword:
Task analysis
Tuning
Collaboration
Statistics
Sociology
Optimization
Deep learning
Deep neural network
hyperparameter (HP) tuning
multitask learning
期刊
IF:
8.9
论文数:
7.5K
被引数:
7.2W
机构
引用论文
分享收藏ChatGPT and Generative AI: Possibilities for Its Contribution to Lesson Planning, Critical Thinking and Openness in Teacher EducationChatGPT和生成性AI: 其对教师教育中的课程计划，批判性思维和开放性做出贡献的可能性
OAAI
OAAI分享收藏Meta-learning for evolutionary parameter optimization of classifiers用于分类器进化参数优化的元学习.png)
MACHINE LEARNINGOAAI
MACHINE LEARNINGIF2.9
OAAI分享收藏分享收藏
Learning Rates of Regularized Regression With Multiple Gaussian Kernels for Multi-Task Learning
PREAI
分享收藏
查看更多内容