000 02516 a2200385 4500
005 20260214162316.0
008 260214b |||||||| |||| 00| 0 eng d
020 _a9781611978551
082 _a519.6 BRA
100 _aBraun, Gabor
245 _aConditional gradient methods: from core principles to AI applications
260 _aPhiladelphia:
_bSociety for Industrial and Applied Mathematics (SIAM),
_c2025.
300 _aix, 195p.:
_bcol., ill.; pbk.:
_c25 cm.
440 _aMOS-SIAM Series on Optimization
504 _aInclude Bibliography, Glossary and Index
520 _aConditional 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 guides readers through the foundations of constrained optimization and into cutting-edge territory—including stochastic, online, and distributed settings—by uniting deep theoretical insights with practical considerations, and uses a clear narrative, rigorous proofs, and illuminating illustrations to demystify adaptive variants, away-steps, and the nuances of dealing with structured convex sets. Most of the algorithms in the book are implemented in the FrankWolfe.jl Julia package and available on a supplementary website. https://epubs.siam.org/doi/book/10.1137/1.9781611978568
650 _aConditional Gradient Methods
650 _aFrank–Wolfe Algorithm
650 _aConstrained Optimization
650 _aFirst-order Methods
650 _aLinear Minimization Oracle (LMO)
650 _aProjection-free Algorithms
650 _aConvex Optimization
650 _aAdaptive Step Sizes
650 _aAway-Step Frank–Wolfe
650 _aFully-Corrective Frank–Wolfe
650 _aMathematical Optimization Society
700 _a Carderera, Alejandro
_eCo-author
700 _aCombettes, Cyrille W.
_eCo-author
700 _aHassani, Hamed
_eCo-author
700 _aKarbasi, Amin
_eCo-author
700 _aMokhtari, Aryan
_eCo-author
700 _aPokutta, Sebastian
_eCo-author
942 _cTD
_2ddc
999 _c64216
_d64216