SOURCE-LINKED INTELLIGENCE

Generalization Analysis of Distributed Kernel-based Robust Gradient Descent Algorithms

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

In this paper, we investigate the generalization performance of distributed gradient descent algorithms in a reproducing kernel Hilbert space under a robust loss function $l_σ$. By exploiting the spectral characterization of gradient descent together with the intrinsic properties of robust loss functions, we establish optimal learning rates for the distributed kernel-based robust gradient descent (DKRGD) algorithm with an appropriately chosen scale parameter $σ$. The proposed parameter choice of $σ$ simultaneously alleviates the saturation phenomenon and guarantees statistical robustness. A ke

Read original source ↗ Open in workspace

recordType

paper

region

Global