000			02300nam a2200349 i 4500
001			CR9781009128490
003			UkCbUP
005			20240919172802.0
006			m|||||o||d||||||||
007			cr||||||||||||
008			210627s2022||||enk o ||1 0|eng|d
020			_a9781009128490 (ebook)
020			_z9781009123235 (hardback)
040			_aUkCbUP _beng _erda _cUkCbUP
050	0	0	_aQ325.5 _b.C69 2022
082	0	4	_a006.31 _223
100	1		_aCouillet, Romain, _d1983- _eauthor.
245	1	0	_aRandom matrix methods for machine learning / _cRomain Couillet, Grenoble Alpes University, Zhenyu Liao, Huazhong University of Science and Technology.
264		1	_aCambridge, United Kingdom ; New York, NY, USA : _bCambridge University Press, _c2022.
300			_a1 online resource (vi, 402 pages) : _bdigital, PDF file(s).
336			_atext _btxt _2rdacontent
337			_acomputer _bc _2rdamedia
338			_aonline resource _bcr _2rdacarrier
500			_aTitle from publisher's bibliographic system (viewed on 30 Jun 2022).
520			_aThis book presents a unified theory of random matrices for applications in machine learning, offering a large-dimensional data vision that exploits concentration and universality phenomena. This enables a precise understanding, and possible improvements, of the core mechanisms at play in real-world machine learning algorithms. The book opens with a thorough introduction to the theoretical basics of random matrices, which serves as a support to a wide scope of applications ranging from SVMs, through semi-supervised learning, unsupervised spectral clustering, and graph methods, to neural networks and deep learning. For each application, the authors discuss small- versus large-dimensional intuitions of the problem, followed by a systematic random matrix analysis of the resulting performance and possible improvements. All concepts, applications, and variations are illustrated numerically on synthetic as well as real-world data, with MATLAB and Python code provided on the accompanying website.
650		0	_aMachine learning _xMathematics.
650		0	_aMatrix analytic methods.
700	1		_aLiao, Zhenyu, _d1992- _eauthor.
776	0	8	_iPrint version: _z9781009123235
856	4	0	_uhttps://doi.org/10.1017/9781009128490
942			_2ddc _cEB
999			_c9372 _d9372