Random matrix methods for machine learning / Romain Couillet and Zhenyu Liao.

By:

Couillet, Romain, 1983- [author.]

Contributor(s):

Liao, Zhenyu, 1992- [author.]

Material type: Text

TextPublisher: Cambridge, UK ; New York, NY : Cambridge University Press, 2023Description: vii, 402 pages : illustrations ; 25 cmContent type:

text

Media type:

unmediated

Carrier type:

volume

ISBN:

9781009123235

Subject(s):

DDC classification:

006.310151922 C831r 23

LOC classification:

Q325.5 .C69 2023

Contents:

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.

Summary: "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.

Tags from this library: No tags from this library for this title. Log in to add tags.

Holdings
Item type	Current library	Shelving location	Call number	Copy number	Status	Date due	Barcode
Books	Main Library	Circulation Section	CIR 006.310151922 C831r 2023 (Browse shelf(Opens below))	1-1	Available		029350

Browsing Main Library shelves, Shelving location: Circulation Section Close shelf browser (Hides shelf browser)

Previous								Next
Previous	CIR 006.31 P317i 2022 Introduction to machine learning /	CIR 006.31 St296 2023 Statistical modeling in machine learning : concepts and applications /	CIR 006.31 T413 2021 3GE collection on computer science : social media and machine learning.	CIR 006.310151922 C831r 2023 Random matrix methods for machine learning /	CIR 006.3101519542 B341 2022 Bayesian reasoning and Gaussian processes for machine learning applications /	CIR 006.312 C276b 2021 Big data mining and complexity /	CIR 006.312 D262 2017 Data mining	Next

Includes bibliographical references and index.

"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.

There are no comments on this title.

to post a comment.