arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

通过函数牛顿更新学习条件期望算子

Learning Conditional Expectation Operators via Functional Newton Updates

Thiago Ramos, Alek Fröhlich, Daniel Perazzo, Massimiliano Pontil

arXiv 2609.35598首次发表:更新:

发表机构

Federal University of São Carlos; Istituto Italiano di Tecnologia; University of Genoa; University College London(圣卡洛斯联邦大学; 意大利技术研究院; 热那亚大学; 伦敦大学学院)

机构由 AI 辅助整理,请以论文原文为准。

AI 中文总结

提出函数谱牛顿方法(FSNM),通过交替函数牛顿更新和提升回归树,无需固定基即可学习条件期望算子的低秩谱结构,实现高效多条件查询。

AI 中文摘要

我们提出了函数谱牛顿方法(FSNM),用于学习条件期望算子的主要奇异结构,而无需固定基或再生核希尔伯特空间。FSNM通过交替进行函数牛顿更新来拟合中心化联合到乘积密度比核的低秩表示。每次更新简化为一个预处理回归,我们通过向量值回归树的逐步提升过程来近似该回归。在总体水平上,我们建立了下降性质,并在相对弱学习器精度条件下获得了$O(1/T)$的最佳迭代块平稳性速率,同时证明了在完全中心化的$L^2$空间上,每个非退化局部最小值都是全局最优的秩-$d$近似。合成实验表明,FSNM能够恢复低秩密度比及其主要谱结构,并且学习到的同一核可以回答多个条件查询而无需重新拟合。

英文摘要

We introduce the Functional Spectral-Newton Method (FSNM) for learning the leading singular structure of a conditional expectation operator without fixing a basis or reproducing kernel Hilbert space. FSNM fits a low-rank representation of the centered joint-to-product density ratio kernel by alternating functional Newton updates. Each update reduces to a preconditioned regression, which we approximate with vector-valued regression trees in a stagewise boosting procedure. At the population level, we establish descent and an $O(1/T)$ best-iterate block-stationarity rate under a relative weak-learner accuracy condition, and show that every nondegenerate local minimum over the full centered $L^2$ spaces is a globally optimal rank-$d$ approximation. Synthetic experiments show that FSNM recovers a low-rank density ratio and its leading spectral structure, and that the same learned kernel can answer multiple conditional queries without refitting.

论文原文

arXiv 摘要页 · PDF 原文 · HTML 原文

↑