Metric Learning In An RKHS

Abstract

Metric learning from a set of triplet comparisons in the form of "Do you think item h is more similar to item i or item j?", indicating similarity and differences between items, plays a key role in various applications including image retrieval, recommendation systems, and cognitive psychology. The goal is to learn a metric in the RKHS that reflects the comparisons. Nonlinear metric learning using kernel methods and neural networks have shown great empirical promise. While previous works have addressed certain aspects of this problem, there is little or no theoretical understanding of such methods. The exception is the special (linear) case in which the RKHS is the standard Euclidean space \(\mathbb\{R\}^d\); there is a comprehensive theory for metric learning in \(\mathbb\{R\}^d\). This paper develops a general RKHS framework for metric learning and provides novel generalization guarantees and sample complexity bounds. We validate our findings through a set of simulations and experime

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytatli2025metric

Related papers

• Discriminative Learning Of Similarity And Group Equivariant Representations (2018)0.00
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Discrete Scale-invariant Metric Learning For Efficient Collaborative Filtering (2025)0.00
• Dynamic Metric Learning From Pairwise Comparisons (2016)3.58
• Metric Learning On Manifolds (2019)0.00
• Neural Bregman Divergences For Distance Learning (2022)0.00
• Sparse Online Relative Similarity Learning (2021)2.26
• Multi-feature Distance Metric Learning For Non-rigid 3D Shape Retrieval (2019)5.84