基于Moreau-Yosida正则化的双层超参数优化
Stabilizing Bi-Level Hyperparameter Optimization using Moreau-Yosida Regularization
摘要：
本文提出用Moreau-Yosida包络线来稳定双层超参数优化求解器的收敛行为，并介绍了Moreau-Yosida正则化超参数优化（MY-HPO）算法。对MY-HPO解的正确性和初始收敛性进行了理论分析。我们的实证结果表明，在固定的计算预算的损失值显着改善，相比，最先进的双层HPO求解器。
英文摘要：
This research proposes to use the Moreau-Yosida envelope to stabilize the convergence behavior of bi-level Hyperparameter optimization solvers, and introduces the new algorithm called Moreau-Yosida regularized Hyperparameter Optimization (MY-HPO) algorithm. Theoretical analysis on the correctness of the MY-HPO solution and initial convergence analysis is also provided. Our empirical results show significant improvement in loss values for a fixed computation budget, compared to the state-of-art bi-level HPO solvers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
