arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07084math.NAcs.NAmath.STstat.COstat.TH
收藏

面向机器学习、偏微分方程与统计学的再生核方法

Reproducing kernel methods for machine learning, PDEs, and statistics

Philippe G. LeFloch, Jean-Marc Mercier, Shohruh Miryusupov

AI总结:

本专著构建了基于RKHS与OT的统一核方法框架,奠定理论基础并提出核的算子视角,同时将其应用于机器学习、物理信息建模、强化学习、数学金融四大领域。

摘要:

本专著构建了一个以应用为导向的统一核方法框架,其理论基础为再生核希尔伯特空间(RKHS,reproducing kernel Hilbert spaces)与最优传输(OT,optimal transport)。第一部分奠定了正定核、离散与连续RKHS、核工程与尺度映射、通过核偏差/最大均值差异(MMD,maximum mean discrepancy)进行误差评估的理论与数值基础,并提出了核的系统化算子视角。在该视角下,投影算子、梯度算子、散度算子与拉普拉斯-贝尔特拉米算子可直接由核构造,从而得到微分算子的离散类似物与变分工具,将学习与偏微分方程(PDE)风格的建模关联起来。第二部分转向四个领域的实际应用。在机器学习领域,我们处理了监督与无监督任务,随后开发了基于RKHS的生成建模,对比了密度方法与投影方法,并结合OT与可扩展的组合分配对其进行增强;我们提出了可降低计算负担的聚类策略,可支持大规模回归与传输任务。在物理信息建模领域,我们提出了针对椭圆型与时变偏微分方程的无网格核离散方法,讨论了自动微分技术,并提出了高阶离散近似方案。在强化学习领域,我们构建了核Q学习与非参数HJB方法,并展示了核算子如何在连续状态、离散动作任务上得到样本高效的基线方法。在数学金融领域,我们构建了非参数时间序列模型与市场生成器,研究了定价的基准测试与外推方法,并将该框架应用于压力测试与投资组合方法。

英文摘要:

This monograph develops a unified, application-driven framework for kernel methods grounded in reproducing kernel Hilbert spaces (RKHS) and optimal transport (OT). Part I lays the theoretical and numerical foundations on positive-definite kernels; discrete and continuous RKHS; kernel engineering and scaling maps; error assessment via kernel discrepancy/maximum mean discrepancy (MMD); and a systematic operator view of kernels. In this viewpoint, projection, gradient, divergence, and Laplace-Beltrami operators are built directly from kernels, enabling discrete analogues of differential operators and variational tools that connect learning with PDE-style modeling. Part II turns to practice across four domains. In machine learning, we treat supervised and unsupervised tasks, then develop RKHS-based generative modeling, contrasting density and projection approaches and enhancing them with OT and scalable, combinatorial assignments. We introduce clustering strategies that reduce computational burden and support large-scale regression and transport. In physics-informed modeling, we present mesh-free kernel discretizations for elliptic and time-dependent PDEs, discuss automatic differentiation, and propose high-order discrete approximations. In reinforcement learning, we formulate kernel Q-learning and non-parametric HJB methods, and show how kernel operators yield sample-efficient baselines on continuous-state, discrete-action tasks. In mathematical finance, we build nonparametric time-series models and market generators, study benchmarking and extrapolation for pricing, and apply the framework to stress testing and portfolio methods.

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。

↑