Reproducing Kernel Methods for Machine Learning, PDEs, and Statistics (Paperback)

Philippe G. LeFloch

ISBN 10: 1611979161 / ISBN 13: 9781611979169

Published by Society for Industrial & Applied Mathematics,U.S., New York, 2026

About this Item

Paperback. This monograph develops a unified, application-driven framework for kernel methods grounded in reproducing kernel Hilbert spaces and optimal transport. The primary goal is to tackle industrial cases from computational physics and mathematical finance and discuss applications across various areas, such as statistics, or artificial intelligence (physics-informed systems, reinforcement learning, machine learning, generative methods, etc.).Reproducing Kernel Methods for Machine Learning, PDEs, and Statistics is divided into two parts, theoretical principles and the techniques employed in their applications; contains numerous applications in engineering, finance, and machine learning; and provides a framework for designing numerically efficient, large-scale dataset strategies. Shipping may be from our UK warehouse or from our Australian or US warehouses, depending on stock availability.

Seller Inventory # 9781611979169

Bibliographic Details

• Title: Reproducing Kernel Methods for Machine Learning, PDEs, and Statistics (Paperback)
• Publisher: Society for Industrial & Applied Mathematics,U.S., New York
• Publication Date: 2026
• Language: English
• ISBN 10: 1611979161
• ISBN 13: 9781611979169
• Binding: Paperback
• Condition: new

About this title

Synopsis

This monograph develops a unified, application-driven framework for kernel methods grounded in reproducing kernel Hilbert spaces and optimal transport. The primary goal is to tackle industrial cases from computational physics and mathematical finance and discuss applications across various areas, such as statistics, or artificial intelligence (physics-informed systems, reinforcement learning, machine learning, generative methods, etc.).

Reproducing Kernel Methods for Machine Learning, PDEs, and Statistics is divided into two parts, theoretical principles and the techniques employed in their applications; contains numerous applications in engineering, finance, and machine learning; and provides a framework for designing numerically efficient, large-scale dataset strategies.

About the Author

P.G. LeFloch is a research professor at the Laboratoire Jacques-Louis Lions, Sorbonne University, and at the Centre National de la Recherche Scientifique (CNRS).

J.-M. Mercier and S. Miryusupov are permanent researchers at the financial compan MPG Partners, based in Paris.