Saved in:
Bibliographic Details
Main Authors: Zhang, Junhong, Lai, Zhihui
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.17765
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909621189345280
author Zhang, Junhong
Lai, Zhihui
author_facet Zhang, Junhong
Lai, Zhihui
contents Kernel methods are powerful tools for nonlinear learning with well-established theory. The scalability issue has been their long-standing challenge. Despite the existing success, there are two limitations in large-scale kernel methods: (i) The memory overhead is too high for users to afford; (ii) existing efforts mainly focus on kernel ridge regression (KRR), while other models lack study. In this paper, we propose Joker, a joint optimization framework for diverse kernel models, including KRR, logistic regression, and support vector machines. We design a dual block coordinate descent method with trust region (DBCD-TR) and adopt kernel approximation with randomized features, leading to low memory costs and high efficiency in large-scale learning. Experiments show that Joker saves up to 90\% memory but achieves comparable training time and performance (or even better) than the state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17765
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Joker: Joint Optimization Framework for Lightweight Kernel Machines
Zhang, Junhong
Lai, Zhihui
Machine Learning
Kernel methods are powerful tools for nonlinear learning with well-established theory. The scalability issue has been their long-standing challenge. Despite the existing success, there are two limitations in large-scale kernel methods: (i) The memory overhead is too high for users to afford; (ii) existing efforts mainly focus on kernel ridge regression (KRR), while other models lack study. In this paper, we propose Joker, a joint optimization framework for diverse kernel models, including KRR, logistic regression, and support vector machines. We design a dual block coordinate descent method with trust region (DBCD-TR) and adopt kernel approximation with randomized features, leading to low memory costs and high efficiency in large-scale learning. Experiments show that Joker saves up to 90\% memory but achieves comparable training time and performance (or even better) than the state-of-the-art methods.
title Joker: Joint Optimization Framework for Lightweight Kernel Machines
topic Machine Learning
url https://arxiv.org/abs/2505.17765