[2410.10523] Machine Learning for Inverse Problems and Data Assimilation

Abstract:The aim of these notes is to demonstrate the potential for ideas in machine learning to impact on the fields of inverse problems and data assimilation. The perspective is one that is primarily aimed at researchers from inverse problems and/or data assimilation who wish to see a mathematical presentation of machine learning as it pertains to their fields. As a by-product, we include a succinct mathematical treatment of various fundamental underpinning topics in machine learning, and adjacent areas of (computational) mathematics.

View PDF HTML (experimental) Abstract:The aim of this book is to demonstrate the potential for ideas in machine learning to impact on the fields of inverse problems and data assimilation. The perspective is one that is primarily aimed at researchers from inverse problems and/or data assimilation who wish to see a mathematical presentation of machine learning as it pertains to their fields. As a by-product, we include a succinct mathematical treatment of various fundamental underpinning topics in machine learning, and adjacent areas of (computational) mathematics. Comments: 377 pages…

saved by

• Didier Lampard

related reading

• Manifold learning: what, how, and whyarxiv.org
• [2403.14606] The Elements of Differentiable Programmingarxiv.org
• The Barron Space and the Flow-induced Function Spaces for Neural Network Modelsarxiv.org
• course_stat_rl.pdfmit.edu
• Deep Learning is Not So Mysterious or Differentarxiv.org
• Pen and Paper Exercises in Machine Learningarxiv.org
• The Little Book of Deep Learningfleuret.org
• [1707.01415] Machine Learning, Deepest Learning: Statistical Data Assimilation Problemsarxiv.org
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• understanding-machine-learning-theory-algorithms.pdfcs.huji.ac.il
• [2604.21691] There Will Be a Scientific Theory of Deep Learningarxiv.org
• 2404.17625arxiv.org