Conditional Gradient Methods: From Core Principles to AI Applications - Softcover

Braun, Gábor; Carderera, Alejandro; Combettes, Cyrille W.; Hassani, Hamed; Karbasi, Amin; Mokhtari, Aryan; Pokutta, Sebastian

Softcover

ISBN 10: 1611978556 ISBN 13: 9781611978551

Verlag: Society for Industrial & Applied Mathematics,U.S., 2025

Inhaltsangabe

Conditional Gradient Methods: From Core Principles to AI Applications offers a definitive and modern treatment of one of the most elegant and versatile algorithmic families in optimization: the Frank–Wolfe method and its many variants. Originally proposed in the 1950s, these projection-free techniques have seen a powerful resurgence, now playing a central role in machine learning, signal processing, and large-scale data science.

This comprehensive monograph unites deep theoretical insights with practical considerations, guiding readers through the foundations of constrained optimization and into cutting-edge territory, including stochastic, online, and distributed settings. With a clear narrative, rigorous proofs, and illuminating illustrations, the book demystifies adaptive variants, away-steps, and the nuances of dealing with structured convex sets. A FrankWolfe.jl Julia package that implements most of the algorithms in the book is available on a supplementary website.

Über diesen Titel

Über die Autorin bzw. den Autor

Sebastian Pokutta is Vice President of the Zuse Institute Berlin (ZIB) and Professor of Mathematics at TU Berlin.

Gábor Braun is currently a member of Zuse Institute Berlin.

Hamed Hassani is an associate professor of the Electrical and Systems Engineering Department, Computer and Information Systems Department, and the Department of Statistics and Data Science at the University of Pennsylvania.

Alejandro Carderera is a Senior Applied Researcher at GitHub, working in Copilot's Applied Science and Models team, focusing on code completions and code review.

Aryan Mokhtari is an Assistant Professor in the Electrical and Computer Engineering Department of the University of Texas at Austin, where he holds the Fellow of Texas Instruments/Kilby.

Cyrille Combettes is a quantitative researcher at Capital Fund Management in Paris.

Amin Karbasi is Chief Scientist at Robust Intelligence and a professor at Yale University.

Details zur Ausgabe

• Verlag: Society for Industrial & Applied Mathematics,U.S.
• Erscheinungsdatum: 2025
• Sprache: Englisch
• ISBN 10: 1611978556
• ISBN 13: 9781611978551
• Einband: Taschenbuch
• Anzahl der Seiten: 198
• Kontakt zum Hersteller: Nicht verfügbar
• Verantwortliche Person: Buchbär; info@buchbaer.de; ; Weberstr. 67; Osnabrück; 49084; Deutschland