Optimization Algorithms for Data Analysis
Stephen J Wright (swrightcs.wisc.edu)
Abstract: We describe the fundamentals of algorithms for minimizing a smooth nonlinear function, and extensions of these methods to the sum of a smooth function and a convex nonsmooth function. Such objective functions are ubiquitous in data analysis applications, as we illustrate using several examples. We discuss methods that make use of gradient (first-order) information about the smooth part of the function, and also Newton methods that make use of Hessian (second-order) information. Convergence and complexity theory is outlined for each approach.
Keywords: Optimization, Data Analysis
Category 1: Nonlinear Optimization (Unconstrained Optimization )
Category 2: Convex and Nonsmooth Optimization (Nonsmooth Optimization )
Category 3: Applications -- Science and Engineering (Data-Mining )
Citation: To appear in "Mathematics of Data," AMS / Park City Mathematics Institute Series, 2017.
Entry Submitted: 12/01/2016
Modify/Update this entry
|Visitors||Authors||More about us||Links|
Search, Browse the Repository
Give us feedback
|Optimization Journals, Sites, Societies|