.png){kind=icon}
.png){kind=icon}
Return
Automated deep learning by recurrent hyperparameter optimization
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-026-72413-9.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Optimizing hyperparameters of deep learning models for specific tasks requires substantial domain expertise and computational resources, remaining challenging in automated deep learning. Existing hyperparameter optimization (HPO) methods are restricted to limited discrete hyperparameter types, rely on manual priors, and fail to scale to large datasets. This paper presents Rocket, a recurrent HPO framework that automates the tuning of mixed-type hyperparameters by self-play reinforcement learning, requiring no prior domain knowledge. A policy agent is developed to learn from historical experience and progressively refine its strategy through iterative interactions with the target model. To address severe reward delay on large-scale datasets, a reward approximation mechanism is designed for data subsets, accelerating policy learning by up to 80X. Across 8 deep learning tasks and 32 benchmarks, Rocket enables target models to achieve state-of-the-art performance from scratch, matching expert-tuned results. In real industrial deployment, Rocket reduces optimization time by 13.4-fold and cost by 73%. Rocket introduces a self-play RL framework for automated hyperparameter optimization, handling mixed types without priors. It scales large datasets via reward approximation, achieving expert-level performance while cutting time and cost in real-world deployments.
Keywords:
Hyperparameter Optimization
Deep Learning
Reinforcement Learning
Self-Play
Automated Machine Learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
15.7
Papers:
9.2W
Citations:
91.2W
View more organizations