Generalization Bounds on Multi-Kernel Learning with Mixed Datasets

2022/05/15 by Lan V. Truong, Truong, Lan V.
Computer Science · #Domain Adaptation and Few-Shot Learning #Machine Learning and Algorithms #Machine Learning and ELM

paper · pdf · doi:10.48550/arxiv.2205.07313

Abstract

This paper presents novel generalization bounds for the multi-kernel learning problem. Motivated by applications in sensor networks and spatial-temporal models, we assume that the dataset is mixed where each sample is taken from a finite pool of Markov chains. Our bounds for learning kernels admit O(√(log m)) dependency on the number of base kernels and O(1/√(n)) dependency on the number of training samples. However, some O(1/√(n)) terms are added to compensate for the dependency among samples compared with existing generalization bounds for multi-kernel learning with i.i.d. datasets.

Related

• Generalization Guarantees for a Binary Classification Framework for Two-Stage Multiple Kernel Learning
• A Note on Improved Loss Bounds for Multiple Kernel Learning
• New Generalization Bounds for Learning Kernels
• Multi-Task Learning Using Neighborhood Kernels
• A Unifying View of Multiple Kernel Learning