OPTIMIZATION FOR DATA ANALYSIS

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. Review: poorly written & explained - very poorly written & explained.. sections of it are completely incomprehensible ...you cannot easily self-study this book Review: Terrible for people who are new to the field of optimization - While this book contains a collection of fundamental results in the field, it is difficult to recommend this book to learn the subject. The text lacks clarity, and seems to move from one result to the next without much explanation. The proofs are hard to follow, often omitting important steps, and, to a reader who is unfamiliar with the field, seemingly draw conclusions from thin air. In addition, authors often use unfamiliar concepts and notation without explaining their meaning, sometimes making the text impenetrable to people who are new to optimization theory.