KerJEPA：核差异用于欧几里得自监督学习
KerJEPA: Kernel Discrepancies for Euclidean Self-Supervised Learning
AI总结：
KerJEPA通过引入基于核的正则化器，改进了自监督学习中欧几里得表示的稳定性与泛化能力。
摘要：
最近在自监督联合嵌入预测架构（JEPAs）中的突破性进展表明，将欧几里得表示正则化为各向同性高斯先验可以带来训练稳定性和下游泛化性的可证明收益。我们介绍了一种新的、灵活的KerJEPAs家族，即具有基于核的正则化器的自监督学习算法。该家族的一个实例对应于最近引入的LeJEPA Epps-Pulley正则化器，该正则化器用高斯先验和高斯核近似切片最大均值差异（MMD）。通过扩展可行核和先验的类别，并计算切片MMD的高维极限的闭式表达式，我们开发了具有若干有利属性的替代KerJEPAs，包括改进的训练稳定性和设计灵活性。
英文摘要：
Recent breakthroughs in self-supervised Joint-Embedding Predictive Architectures (JEPAs) have established that regularizing Euclidean representations toward isotropic Gaussian priors yields provable gains in training stability and downstream generalization. We introduce a new, flexible family of KerJEPAs, self-supervised learning algorithms with kernel-based regularizers. One instance of this family corresponds to the recently-introduced LeJEPA Epps-Pulley regularizer which approximates a sliced maximum mean discrepancy (MMD) with a Gaussian prior and Gaussian kernel. By expanding the class of viable kernels and priors and computing the closed-form high-dimensional limit of sliced MMDs, we develop alternative KerJEPAs with a number of favorable properties including improved training stability and design flexibility.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
