Optimization for Data Analysis
- ISBN-10
- 1009019120
- ISBN-13
- 9781009019125
- Category
- Mathematics
- Pages
- 239
- Language
- English
- Published
- 2022-04-21
- Publisher
- Cambridge University Press
- Authors
- Stephen J. Wright, Benjamin Recht
Description
Optimization techniques are at the core of data science, including data analysis and machine learning. An understanding of basic optimization techniques and their fundamental properties provides important grounding for students, researchers, and practitioners in these areas. This text covers the fundamentals of optimization algorithms in a compact, self-contained way, focusing on the techniques most relevant to data science. An introductory chapter demonstrates that many standard problems in data science can be formulated as optimization problems. Next, many fundamental methods in optimization are described and analyzed, including: gradient and accelerated gradient methods for unconstrained optimization of smooth (especially convex) functions; the stochastic gradient method, a workhorse algorithm in machine learning; the coordinate descent approach; several key algorithms for constrained optimization problems; algorithms for minimizing nonsmooth functions arising in data science; foundations of the analysis of nonsmooth functions and optimization duality; and the back-propagation approach, relevant to neural networks.
Get the book
Similar books
-
Integral Geometry and Tomography: Proceedings of the AMS-IMS-SIAM Joint Summer Research Conference, Held June 24-30, 1989, with Support from the...
By Eric Grinberg, Eric Todd QuintoIn Section 2 we will deal with the “discrete” case. Let S be a locally finite tree T endowed with the natural integer-valued distance function: the ...
-
Ordinary Differential Equations and Linear Algebra: A Systems Approach
By Todd Kapitula... for in this case [yp](s)=s[yp](s), [yp](s)=s2[yp](s). As we will see in the examples, this assumption also makes it possible to deal with the initial ...
-
Cognition and Intractability: A Guide to Classical and Parameterized Complexity Analysis
By Iris van Rooij, Mark Blokpoel, Johan Kwisthoutx,y∈S δ(x,y) is maximum. u(x) + ADDITIVE SUBSET CHOICE Input: A set X = {x1 ,x2 ... F Tractability cycle Test 8.2 How (Not) to Deal with Intractability 173.
-
Mymathlab -- Standalone Access Card
By Pearson Education, David P Pearson Education, Hall H Pearson EducationSeveral versions of Pearson's MyLab & Mastering products exist for each title, including customized versions for individual schools, and registrations are not transferable.
-
Mymathlab Student Acc Kit + Intro Alg Wrkshts
By Inc. Pearson EducationMymathlab Student Acc Kit + Intro Alg Wrkshts
-
Pearson Mathematics 7: H.P
By Pearson Education Australia StaffPearson Mathematics homework program for Year 7 provides tear-out sheets which correspond with student book sections, providing systematic and cumulative skills revision of basic skills and current class topics in the form of take-home ...
-
Worksheets for Classroom Or Lab Practice for Intermediate Algebra: Graphs & Models
By Addison-WesleyWorksheets for Classroom Or Lab Practice for Intermediate Algebra: Graphs & Models
-
Pearson Mathematics New South Wales 8 Student Book: Australian Curriculum
By Pearson Education Australia Staff, Gael McLeod, David CoffeyThe Student Book provides an easy-to-use 'nuts and bolts' book at each year level.
-
Matrix Iterative Analysis
By Richard S. Varga... partial differential equations have received a great deal of attention. For excellent bibliographical coverage, see Todd (1956), Richtmyer (1957), ...
-
Mathematical Modelling: Education, Engineering and Economics - ICTMA 12
By C Haines, P Galbraith, W BlumTodd, P. A., McKeen, .l. ... ANALYTICAL SUPPORT PROBLEM SOLVING Cognitive Perspectives on Modelling HOW DO STUDENTS AND TEACHERS DEAL Sodhi and Son 219 NOTE ...