02256cam a22003738i 4500 22467705 CSPC 20250326142730.0 220316s2023 enk b 001 0 eng 2022009569 9781009123235 (hardback) DLC eng rda DLC CSPC pcc Q325.5 .C69 2023 006.310151922 C831r 23 Couillet, Romain, 1983- author. Random matrix methods for machine learning / Romain Couillet and Zhenyu Liao. 2209 Cambridge, UK ; New York, NY : Cambridge University Press, 2023. vii, 402 pages : illustrations ; 25 cm. text txt rdacontent unmediated n rdamedia volume nc rdacarrier Includes bibliographical references and index. Introduction -- Random matrix theory -- Statistical inference in linear models -- Kernel methods -- Large neural networks -- Large-dimensional convex optimization -- Community detection on graphs -- Universality and real data. "Numerous and large dimensional data is now a default setting in modern machine learning (ML). Standard ML algorithms, starting with kernel methods such as support vector machines and graph-based methods like the PageRank algorithm, were however initially designed out of small dimensional intuitions and tend to misbehave, if not completely collapse, when dealing with real-world large datasets. Random matrix theory has recently developed a broad spectrum of tools to help understand this new curse of dimensionality, to help repair or completely recreate the sub-optimal algorithms, and most importantly to provide new intuitions to deal with modern data mining"-- Provided by publisher. Machine learning Mathematics. Matrix analytic methods. Liao, Zhenyu, 1992- author. 7 cbc orignew 1 ecip 20 y-gencatlg ddc 0 BK 23 006.310151922 C831r CIR 2023 0 0 ddc 0 0 CSPC CSPC CIR 2025-03-26 0 CIR 006.310151922 C831r 2023 029350 2025-03-26 13:27:53 1-1 2025-03-26 BK 29346 29346