UID:
almafu_9960118871102883
Format:
1 online resource (vii, 151 pages) :
,
digital, PDF file(s).
Edition:
1st ed.
ISBN:
1-316-88685-9
,
1-316-88482-1
,
1-316-88217-9
Content:
This book bridges theoretical computer science and machine learning by exploring what the two sides can teach each other. It emphasizes the need for flexible, tractable models that better capture not what makes machine learning hard, but what makes it easy. Theoretical computer scientists will be introduced to important models in machine learning and to the main questions within the field. Machine learning researchers will be introduced to cutting-edge research in an accessible format, and gain familiarity with a modern, algorithmic toolkit, including the method of moments, tensor decompositions and convex programming relaxations. The treatment beyond worst-case analysis is to build a rigorous understanding about the approaches used in practice and to facilitate the discovery of exciting, new ways to solve important long-standing problems.
Note:
Title from publisher's bibliographic system (viewed on 28 Sep 2018).
,
Cover -- Half-title -- Dedication -- Title page -- Copyright information -- Table of contents -- Preface -- 1 Introduction -- 2 Nonnegative Matrix Factorization -- 2.1 Introduction -- 2.2 Algebraic Algorithms -- 2.3 Stability and Separability -- 2.4 Topic Models -- 2.5 Exercises -- 3 Tensor Decompositions: Algorithms -- 3.1 The Rotation Problem -- 3.2 A Primer on Tensors -- 3.3 Jennrich's Algorithm -- 3.4 Perturbation Bounds -- 3.5 Exercises -- 4 Tensor Decompositions: Applications -- 4.1 Phylogenetic Trees and HMMs -- 4.2 Community Detection -- 4.3 Extensions to Mixed Models -- 4.4 Independent Component Analysis -- 4.5 Exercises -- 5 Sparse Recovery -- 5.1 Introduction -- 5.2 Incoherence and Uncertainty Principles -- 5.3 Pursuit Algorithms -- 5.4 Prony's Method -- 5.5 Compressed Sensing -- 5.6 Exercises -- 6 Sparse Coding -- 6.1 Introduction -- 6.2 The Undercomplete Case -- 6.3 Gradient Descent -- 6.4 The Overcomplete Case -- 6.5 Exercises -- 7 Gaussian Mixture Models -- 7.1 Introduction -- 7.2 Clustering-Based Algorithms -- 7.3 Discussion of Density Estimation -- 7.4 Clustering-Free Algorithms -- 7.5 A Univariate Algorithm -- 7.6 A View from Algebraic Geometry -- 7.7 Exercises -- 8 Matrix Completion -- 8.1 Introduction -- 8.2 Nuclear Norm -- 8.3 Quantum Golfing -- Bibliography -- Index.
Additional Edition:
ISBN 1-107-18458-4
Language:
English
