000			03933nam a22005775i 4500
001			978-3-030-17076-9
003			DE-He213
005			20220801214744.0
007			cr nn 008mamaa
008			190612s2020 sz | s |||| 0|eng d
020			_a9783030170769 _9978-3-030-17076-9
024	7		_a10.1007/978-3-030-17076-9 _2doi
050		4	_aTK5101-5105.9
072		7	_aTJK _2bicssc
072		7	_aTEC041000 _2bisacsh
072		7	_aTJK _2thema
082	0	4	_a621.382 _223
100	1		_aShi, Bin. _eauthor. _4aut _4http://id.loc.gov/vocabulary/relators/aut _940251
245	1	0	_aMathematical Theories of Machine Learning - Theory and Applications _h[electronic resource] / _cby Bin Shi, S. S. Iyengar.
250			_a1st ed. 2020.
264		1	_aCham : _bSpringer International Publishing : _bImprint: Springer, _c2020.
300			_aXXI, 133 p. 25 illus., 24 illus. in color. _bonline resource.
336			_atext _btxt _2rdacontent
337			_acomputer _bc _2rdamedia
338			_aonline resource _bcr _2rdacarrier
347			_atext file _bPDF _2rda
505	0		_aChapter 1. Introduction -- Chapter 2. General Framework of Mathematics -- Chapter 3. Problem Formulation -- Chapter 4. Development of Novel Techniques of CoCoSSC Method -- Chapter 5. Further Discussions of the Proposed Method -- Chapter 6. Related Work on Geometry of Non-Convex Programs -- Chapter 7. Gradient Descent Converges to Minimizers -- Chapter 8. A Conservation Law Method Based on Optimization -- Chapter 9. Improved Sample Complexity in Sparse Subspace Clustering with Noisy and Missing Observations -- Chapter 10. Online Discovery for Stable and Grouping Causalities in Multi-Variate Time Series -- Chapter 11. Conclusion.
520			_aThis book studies mathematical theories of machine learning. The first part of the book explores the optimality and adaptivity of choosing step sizes of gradient descent for escaping strict saddle points in non-convex optimization problems. In the second part, the authors propose algorithms to find local minima in nonconvex optimization and to obtain global minima in some degree from the Newton Second Law without friction. In the third part, the authors study the problem of subspace clustering with noisy and missing data, which is a problem well-motivated by practical applications data subject to stochastic Gaussian noise and/or incomplete data with uniformly missing entries. In the last part, the authors introduce an novel VAR model with Elastic-Net regularization and its equivalent Bayesian model allowing for both a stable sparsity and a group selection. Provides a thorough look into the variety of mathematical theories of machine learning Presented in four parts, allowing for readers to easily navigate the complex theories Includes extensive empirical studies on both the synthetic and real application time series data.
650		0	_aTelecommunication. _910437
650		0	_aComputational intelligence. _97716
650		0	_aData mining. _93907
650		0	_aInformation storage and retrieval systems. _922213
650		0	_aQuantitative research. _94633
650	1	4	_aCommunications Engineering, Networks. _931570
650	2	4	_aComputational Intelligence. _97716
650	2	4	_aData Mining and Knowledge Discovery. _940252
650	2	4	_aInformation Storage and Retrieval. _923927
650	2	4	_aData Analysis and Big Data. _940253
700	1		_aIyengar, S. S. _eauthor. _4aut _4http://id.loc.gov/vocabulary/relators/aut _940254
710	2		_aSpringerLink (Online service) _940255
773	0		_tSpringer Nature eBook
776	0	8	_iPrinted edition: _z9783030170752
776	0	8	_iPrinted edition: _z9783030170776
776	0	8	_iPrinted edition: _z9783030170783
856	4	0	_uhttps://doi.org/10.1007/978-3-030-17076-9
912			_aZDB-2-ENG
912			_aZDB-2-SXE
942			_cEBK
999			_c76714 _d76714