Mathematical Pictures at a Data Science Exhibition

This text provides deep and comprehensive coverage of the mathematical background for data science, including machine learning, optimal recovery, compressed sensing, optimization, and neural networks. In the past few decades, heuristic methods adopted by big tech companies have complemented existing scientific disciplines to form the new field of Data Science. This text embarks the readers on an engaging itinerary through the theory supporting the field. Altogether, twenty-seven lecture-length chapters with exercises provide all the details necessary for a solid understanding of key topics in data science. While the book covers standard material on machine learning and optimization, it also includes distinctive presentations of topics such as reproducing kernel Hilbert spaces, spectral clustering, optimal recovery, compressed sensing, group testing, and applications of semidefinite programming. Students and data scientists with less mathematical background will appreciate the appendices that provide more background on some of the more abstract concepts.

Table of Contents:
Part I. Machine Learning: 1. Rudiments of Statistical Learning; 2. Vapnik–Chervonenkis Dimension; 3. Learnability for Binary Classification; 4. Support Vector Machines; 5. Reproducing Kernel Hilbert; 6. Regression and Regularization; 7. Clustering; 8. Dimension Reduction; Part II Optimal Recovery: 9. Foundational Results of Optimal Recovery; 10. Approximability Models; 11. Ideal Selection of Observation Schemes; 12. Curse of Dimensionality; 13. Quasi-Monte Carlo Integration; Part III Compressive Sensing: 14. Sparse Recovery from Linear Observations; 15. The Complexity of Sparse Recovery; 16. Low-Rank Recovery from Linear Observations; 17. Sparse Recovery from One-Bit Observations; 18. Group Testing; Part IV Optimization: 19. Basic Convex Optimization; 20. Snippets of Linear Programming; 21. Duality Theory and Practice; 22. Semidefinite Programming in Action; 23. Instances of Nonconvex Optimization; Part V Neural Networks: 24. First Encounter with ReLU Networks; 25. Expressiveness of Shallow Networks; 26. Various Advantages of Depth; 27. Tidbits on Neural Network Training; Appendix A; High-Dimensional Geometry; Appendix B. Probability Theory; Appendix C. Functional Analysis; Appendix D. Matrix Analysis; Appendix E. Approximation Theory.

About the Author :
Simon Foucart is Professor of Mathematics at Texas A&M University, where he was named Presidential Impact Fellow in 2019. He has previously written, together with Holger Rauhut, the influential book A Mathematical Introduction to Compressive Sensing (2013).

Review :
'What a great read and a unique perspective! It contains a beautifully written rigorous treatment of many areas of Mathematical Data Science - perfect for a graduate course or for scholars of related backgrounds. The presentation and 'walk through' of the topic are a great way to motivate its study.' Deanna Needell, University of California, Los Angeles 'The title perfectly captures the book's approach, and the author is a wonderful guide to this gallery. He sticks to the facts and gives a cogent yet thorough description of the most foundational mathematical results. The book will fill in some missing mathematical background for many of us working in data science, and the exercises make it an excellent class text as well.' Stephen Wright, University of Wisconsin - Madison 'With Mathematical Pictures at a Data Science Exhibition, Simon Foucart has deftly illuminated the mathematical side of data science with a rigorous yet accessible treatment. This book, like a good museum, will be a valuable resource for experts, students, and casual enthusiasts.' Richard Baraniuk, Rice University '… an excellent discussion of representative algorithms as used in data science today - one of the best in-depth resources to appear in recent years for a scientist working on new analytic approaches or optimization … Highly recommended.' J. Brzezinski, Choice '… this book acts as a welcome road map for graduate students and researchers in the field. … a wonderful read for young students looking to start their careers in the mathematical and theoretical aspects of data science or for experienced researchers looking to broaden their familiarity with various perspectives on the theory of data science from different fields such as applied mathematics, statistics, or computer science. I certainly appreciate having the book in my library and would recommend it to my own students.' Bamdad Hosseini, SIAMN Review