Couillet, Romain 1983- creator author. Liao, Zhenyu 1992- author. text bibliography enk 2023 monographic eng

print

vii, 402 pages : illustrations ; 25 cm. "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"-- 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. Romain Couillet and Zhenyu Liao. Includes bibliographical references and index. Machine learning Mathematics Matrix analytic methods Q325.5 .C69 2023 006.310151922 C831r 9781009123235 2022009569 DLC 220316 20250326142730.0 22467705 eng