5 papers
RLDISCOVER: LLM-driven co-evolution of reinforcement learning algorithms
Haoran Li, Zengle Ge, Xiaomin Yuan +14
LLM-guided program evolution has enabled discoveries in mathematics and computational optimization, raising the prospect of reinforcement learning (RL) algorithms that self-evolve…
Importance-Aware Scheduling for High-Dimensional Hyperparameter Optimization
Ruinan Wang, Ian Nabney, Mohammad Golbabaee
Hyperparameter Optimization (HPO) is essential for building high-performing ML/DL models, yet conventional optimizers often struggle in high-dimensional spaces where evaluations ar…
SynLeaF: A Dual-Stage Multimodal Fusion Framework for Synthetic Lethality Prediction Across Pan- and Single-Cancer Contexts
Zheming Xing, Siyuan Zhou, Ruinan Wang +9
Accurate prediction of synthetic lethality (SL) is important for guiding the development of cancer drugs and therapies. SL prediction faces significant challenges in the effective…
Grouped Sequential Optimization Strategy -- the Application of Hyperparameter Importance Assessment in Deep Learning
Ruinan Wang, Ian Nabney, Mohammad Golbabaee
Hyperparameter optimization (HPO) is a critical component of machine learning pipelines, significantly affecting model robustness, stability, and generalization. However, HPO is of…
Efficient Hyperparameter Importance Assessment for CNNs
Ruinan Wang, Ian Nabney, Mohammad Golbabaee
Hyperparameter selection is an essential aspect of the machine learning pipeline, profoundly impacting models' robustness, stability, and generalization capabilities. Given the com…