AI RESEARCH
Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates
arXiv CS.LG
•
ArXi:2604.13130v1 Announce Type: new We study learning to learn for regression problems through the lens of hyperparameter tuning. We propose the Langevin Gradient Descent Algorithm (LGD), which approximates the mean of the posterior distribution defined by the loss function and regularizer of a convex regression task. We prove the existence of an optimal hyperparameter configuration for which the LGD algorithm achieves the Bayes' optimal solution for squared loss.