Saved in:
Bibliographic Details
Main Authors: Sui, Hangke, Wang, Yuqing, Do, Minh N
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.16678
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917417769238528
author Sui, Hangke
Wang, Yuqing
Do, Minh N
author_facet Sui, Hangke
Wang, Yuqing
Do, Minh N
contents Contrastive objectives power state-of-the-art multimodal models, but their training remains slow, relying on long stochastic optimization. We propose a Unified Framework for Efficient Contrastive Alignment via Kernels (UniCon), which spans linear and nonlinear encoders as well as one-to-one and many-to-many alignments. At its core, UniCon introduces the contrastive similarity weight matrix $S(γ)$, which enables closed-form global solutions that provably replace minibatch back-propagation with exact updates. Through the lens of reproducing kernel Hilbert spaces (RKHS), UniCon provides a kernelized perspective that unifies contrastive alignment and reveals its connection to spectral methods. To validate the theory, we conduct experiments on synthetic, unimodal, multimodal, and zero-shot tasks, demonstrating that UniCon achieves substantial efficiency gains while preserving generality and strong empirical performance.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16678
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UniCon: Unified Framework for Efficient Contrastive Alignment via Kernels
Sui, Hangke
Wang, Yuqing
Do, Minh N
Machine Learning
Contrastive objectives power state-of-the-art multimodal models, but their training remains slow, relying on long stochastic optimization. We propose a Unified Framework for Efficient Contrastive Alignment via Kernels (UniCon), which spans linear and nonlinear encoders as well as one-to-one and many-to-many alignments. At its core, UniCon introduces the contrastive similarity weight matrix $S(γ)$, which enables closed-form global solutions that provably replace minibatch back-propagation with exact updates. Through the lens of reproducing kernel Hilbert spaces (RKHS), UniCon provides a kernelized perspective that unifies contrastive alignment and reveals its connection to spectral methods. To validate the theory, we conduct experiments on synthetic, unimodal, multimodal, and zero-shot tasks, demonstrating that UniCon achieves substantial efficiency gains while preserving generality and strong empirical performance.
title UniCon: Unified Framework for Efficient Contrastive Alignment via Kernels
topic Machine Learning
url https://arxiv.org/abs/2604.16678