Conditional Gradient Methods: From Core Principles to AI Applications

Explores how quantum computing redefines optimization by tackling intricate challenges with rigorous methods and clear insights into computational complexity. This self-contained exploration demystifies conditional gradient techniques and highlights major algorithmic advances in quantum and AI applications. This book is a self-contained introduction to quantum algorithms with an emphasis on quantum optimization, that is, quantum algorithms to solve optimization problems. The book provides all the tools necessary to understand the benefits and drawbacks of quantum optimization algorithms, paying particular attention to provable guarantees and computational complexity. The first comprehensive treatment of quantum optimization, Conditional Gradient Methods: From Core Principles to AI Applications provides a rigorous introduction to the computational model of quantum computers, contains detailed discussion of some of the most important developments in quantum optimization algorithms, and summarizes the most important developments in the open literature.