Alternating Direction Method of Multipliers for Machine Learning

Machine learning heavily relies on optimization algorithms to solve its learning models. Constrained problems constitute a major type of optimization problem, and the alternating direction method of multipliers (ADMM) is a commonly used algorithm to solve constrained problems, especially linearly constrained ones. Written by experts in machine learning and optimization, this is the first book providing a state-of-the-art review on ADMM under various scenarios, including deterministic and convex optimization, nonconvex optimization, stochastic optimization, and distributed optimization. Offering a rich blend of ideas, theories and proofs, the book is up-to-date and self-contained. It is an excellent reference book for users who are seeking a relatively universal algorithm for constrained problems. Graduate students or researchers can read it to grasp the frontiers of ADMM in machine learning in a short period of time.

機器學習在解決學習模型時，極度依賴優化演算法。受限制問題是優化問題的一個主要類型，而交替方向乘子法（ADMM）是一種常用的算法，尤其用於解決線性受限制問題。本書由機器學習和優化領域的專家撰寫，是第一本在各種情境下對ADMM進行最新綜述的書籍，包括確定性和凸優化、非凸優化、隨機優化和分散式優化。本書提供了豐富的思想、理論和證明，並且內容最新且自成一體。對於尋求一種相對通用的受限制問題算法的使用者來說，這是一本優秀的參考書。研究生或研究人員可以通過閱讀本書，在短時間內掌握ADMM在機器學習中的前沿知識。

Zhouchen Lin is a leading expert in the fields of machine learning and optimization. He is currently a professor with the Key Laboratory of Machine Perception (Ministry of Education), School of Artificial Intelligence, Peking University. Prof. Lin served as an area chair many times for prestigious conferences, including CVPR, ICCV, NIPS/NeurIPS, ICML, ICLR, IJCAI and AAAI. He is a Program Co-Chair of ICPR 2022 and a Senior Area Chair of ICML 2022. Prof. Lin is an associate editor of the International Journal of Computer Vision and the Optimization Methods and Software. He is a Fellow of CSIG, IAPR and IEEE.

Huan Li received a doctoral degree in machine learning from Peking University in 2019. He is currently an assistant researcher at the School of Artificial Intelligence, Nankai University. His research interests include optimization and machine learning.

Cong Fang received a doctoral degree in machine learning from Peking University in 2019. He is currently an assistant professor at the School of Artificial Intelligence, Peking University. His research interests include optimization and machine learning.

周晨林是機器學習和優化領域的領先專家。他目前是北京大學人工智能學院機器感知教育部重點實驗室的教授。林教授多次擔任知名會議的領域主席，包括CVPR、ICCV、NIPS/NeurIPS、ICML、ICLR、IJCAI和AAAI。他是ICPR 2022的程序主席和ICML 2022的高級領域主席。林教授是《國際計算機視覺期刊》和《優化方法與軟件》的副編輯。他是CSIG、IAPR和IEEE的會士。

李煥於2019年在北京大學獲得機器學習博士學位。他目前是南開大學人工智能學院的助理研究員。他的研究興趣包括優化和機器學習。

從2019年起，方聰在北京大學獲得機器學習博士學位。他目前是北京大學人工智能學院的助理教授。他的研究興趣包括優化和機器學習。