{"product_id":"optimization-for-learning-and-control-9781119809135","title":"Optimization for Learning and Control","description":"\u003cb\u003eBook Synopsis\u003c\/b\u003e\u003cbr\u003eOptimization for Learning and Control Comprehensive resource providing a masters' level introduction to optimization theory and algorithms for learning and control Optimization for Learning and Control describes how optimization is used in these domains, giving a thorough introduction to both unsupervised learning, supervised learning, and reinforcement learning, with an emphasis on optimization methods for large-scale learning and control problems.   Several applications areas are also discussed, including signal processing, system identification, optimal control, and machine learning.  Today, most of the material on the optimization aspects of deep learning that is accessible for  students at a Masters' level is focused on surface-level computer programming; deeper knowledge about the optimization methods and the trade-offs that are behind these methods is not provided. The objective of this book is to make this scattered knowledge, currently mainly available in  publications in acad\u003cbr\u003e\u003cbr\u003e\u003cb\u003eTable of Contents\u003c\/b\u003e\u003cbr\u003e\u003cp\u003ePreface xvii\u003c\/p\u003e \u003cp\u003eAcknowledgments xix\u003c\/p\u003e \u003cp\u003eGlossary xxi\u003c\/p\u003e \u003cp\u003eAcronyms xxv\u003c\/p\u003e \u003cp\u003eAbout the Companion Website xxvii\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePart I Introductory Part 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e1 Introduction 3\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e1.1 Optimization 3\u003c\/p\u003e \u003cp\u003e1.2 Unsupervised Learning 3\u003c\/p\u003e \u003cp\u003e1.3 Supervised Learning 4\u003c\/p\u003e \u003cp\u003e1.4 System Identification 4\u003c\/p\u003e \u003cp\u003e1.5 Control 5\u003c\/p\u003e \u003cp\u003e1.6 Reinforcement Learning 5\u003c\/p\u003e \u003cp\u003e1.7 Outline 5\u003c\/p\u003e \u003cp\u003e\u003cb\u003e2 Linear Algebra 7\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e2.1 Vectors and Matrices 7\u003c\/p\u003e \u003cp\u003e2.2 Linear Maps and Subspaces 10\u003c\/p\u003e \u003cp\u003e2.3 Norms 13\u003c\/p\u003e \u003cp\u003e2.4 Algorithm Complexity 15\u003c\/p\u003e \u003cp\u003e2.5 Matrices with Structure 16\u003c\/p\u003e \u003cp\u003e2.6 Quadratic Forms and Definiteness 21\u003c\/p\u003e \u003cp\u003e2.7 Spectral Decomposition 22\u003c\/p\u003e \u003cp\u003e2.8 Singular Value Decomposition 23\u003c\/p\u003e \u003cp\u003e2.9 Moore-Penrose Pseudoinverse 24\u003c\/p\u003e \u003cp\u003e2.10 Systems of Linear Equations 25\u003c\/p\u003e \u003cp\u003e2.11 Factorization Methods 26\u003c\/p\u003e \u003cp\u003e2.12 Saddle-Point Systems 32\u003c\/p\u003e \u003cp\u003e2.13 Vector and Matrix Calculus 33\u003c\/p\u003e \u003cp\u003e\u003cb\u003e3 Probability Theory 40\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e3.1 Probability Spaces 40\u003c\/p\u003e \u003cp\u003e3.2 Conditional Probability 42\u003c\/p\u003e \u003cp\u003e3.3 Independence 44\u003c\/p\u003e \u003cp\u003e3.4 Random Variables 44\u003c\/p\u003e \u003cp\u003e3.5 Conditional Distributions 47\u003c\/p\u003e \u003cp\u003e3.6 Expectations 48\u003c\/p\u003e \u003cp\u003e3.7 Conditional Expectations 50\u003c\/p\u003e \u003cp\u003e3.8 Convergence of Random Variables 51\u003c\/p\u003e \u003cp\u003e3.9 Random Processes 51\u003c\/p\u003e \u003cp\u003e3.10 Markov Processes 53\u003c\/p\u003e \u003cp\u003e3.11 Hidden Markov Models 53\u003c\/p\u003e \u003cp\u003e3.12 Gaussian Processes 56\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePart II Optimization 61\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e4 Optimization Theory 63\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e4.1 Basic Concepts and Terminology 63\u003c\/p\u003e \u003cp\u003e4.2 Convex Sets 66\u003c\/p\u003e \u003cp\u003e4.3 Convex Functions 72\u003c\/p\u003e \u003cp\u003e4.4 Subdifferentiability 80\u003c\/p\u003e \u003cp\u003e4.5 Convex Optimization Problems 84\u003c\/p\u003e \u003cp\u003e4.6 Duality 86\u003c\/p\u003e \u003cp\u003e4.7 Optimality Conditions 90\u003c\/p\u003e \u003cp\u003e\u003cb\u003e5 Optimization Problems 94\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e5.1 Least-Squares Problems 94\u003c\/p\u003e \u003cp\u003e5.2 Quadratic Programs 96\u003c\/p\u003e \u003cp\u003e5.3 Conic Optimization 97\u003c\/p\u003e \u003cp\u003e5.4 Rank Optimization 103\u003c\/p\u003e \u003cp\u003e5.5 Partially Separability 106\u003c\/p\u003e \u003cp\u003e5.6 Multiparametric Optimization 109\u003c\/p\u003e \u003cp\u003e5.7 Stochastic Optimization 111\u003c\/p\u003e \u003cp\u003e\u003cb\u003e6 Optimization Methods 118\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e6.1 Basic Principles 118\u003c\/p\u003e \u003cp\u003e6.2 Gradient Descent 124\u003c\/p\u003e \u003cp\u003e6.3 Newton’s Method 128\u003c\/p\u003e \u003cp\u003e6.4 Variable Metric Methods 134\u003c\/p\u003e \u003cp\u003e6.5 Proximal Gradient Method 137\u003c\/p\u003e \u003cp\u003e6.6 Sequential Convex Optimization 141\u003c\/p\u003e \u003cp\u003e6.7 Methods for Nonlinear Least-Squares 142\u003c\/p\u003e \u003cp\u003e6.8 Stochastic Optimization Methods 144\u003c\/p\u003e \u003cp\u003e6.9 Coordinate Descent Methods 153\u003c\/p\u003e \u003cp\u003e6.10 Interior-Point Methods 155\u003c\/p\u003e \u003cp\u003e6.11 Augmented Lagrangian Methods 161\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePart III Optimal Control 173\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e7 Calculus of Variations 175\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e7.1 Extremum of Functionals 175\u003c\/p\u003e \u003cp\u003e7.2 The Pontryagin Maximum Principle 179\u003c\/p\u003e \u003cp\u003e7.3 The Euler-Lagrange Equations 183\u003c\/p\u003e \u003cp\u003e7.4 Extensions 185\u003c\/p\u003e \u003cp\u003e7.5 Numerical Solutions 188\u003c\/p\u003e \u003cp\u003e\u003cb\u003e8 Dynamic Programming 206\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e8.1 Finite Horizon Optimal Control 206\u003c\/p\u003e \u003cp\u003e8.2 Parametric Approximations 211\u003c\/p\u003e \u003cp\u003e8.3 Infinite Horizon Optimal Control 213\u003c\/p\u003e \u003cp\u003e8.4 Value Iterations 215\u003c\/p\u003e \u003cp\u003e8.5 Policy Iterations 216\u003c\/p\u003e \u003cp\u003e8.6 Linear Programming Formulation 220\u003c\/p\u003e \u003cp\u003e8.7 Model Predictive Control 221\u003c\/p\u003e \u003cp\u003e8.8 Explicit MPC 225\u003c\/p\u003e \u003cp\u003e8.9 Markov Decision Processes 226\u003c\/p\u003e \u003cp\u003e8.10 Appendix 233\u003c\/p\u003e \u003cp\u003e\u003cb\u003ePart IV Learning 243\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003e9 Unsupervised Learning 245\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e9.1 Chebyshev Bounds 245\u003c\/p\u003e \u003cp\u003e9.2 Entropy 246\u003c\/p\u003e \u003cp\u003e9.3 Prediction 254\u003c\/p\u003e \u003cp\u003e9.4 The Viterbi Algorithm 259\u003c\/p\u003e \u003cp\u003e9.5 Kalman Filter on Innovation Form 261\u003c\/p\u003e \u003cp\u003e9.6 Viterbi Decoder 264\u003c\/p\u003e \u003cp\u003e9.7 Graphical Models 266\u003c\/p\u003e \u003cp\u003e9.8 Maximum Likelihood Estimation 269\u003c\/p\u003e \u003cp\u003e9.9 Relative Entropy and Cross Entropy 271\u003c\/p\u003e \u003cp\u003e9.10 The Expectation Maximization Algorithm 273\u003c\/p\u003e \u003cp\u003e9.11 Mixture Models 274\u003c\/p\u003e \u003cp\u003e9.12 Gibbs Sampling 277\u003c\/p\u003e \u003cp\u003e9.13 Boltzmann Machine 278\u003c\/p\u003e \u003cp\u003e9.14 Principal Component Analysis 280\u003c\/p\u003e \u003cp\u003e9.15 Mutual Information 283\u003c\/p\u003e \u003cp\u003e9.16 Cluster Analysis 288\u003c\/p\u003e \u003cp\u003e\u003cb\u003e10 Supervised Learning 297\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e10.1 Linear Regression 297\u003c\/p\u003e \u003cp\u003e10.2 Regression in Hilbert Spaces 300\u003c\/p\u003e \u003cp\u003e10.3 Gaussian Processes 302\u003c\/p\u003e \u003cp\u003e10.4 Classification 304\u003c\/p\u003e \u003cp\u003e10.5 Support Vector Machines 306\u003c\/p\u003e \u003cp\u003e10.6 Restricted Boltzmann Machine 310\u003c\/p\u003e \u003cp\u003e10.7 Artificial Neural Networks 312\u003c\/p\u003e \u003cp\u003e10.8 Implicit Regularization 316\u003c\/p\u003e \u003cp\u003e\u003cb\u003e11 Reinforcement Learning 327\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e11.1 Finite Horizon Value Iteration 327\u003c\/p\u003e \u003cp\u003e11.2 Infinite Horizon Value Iteration 330\u003c\/p\u003e \u003cp\u003e11.3 Policy Iteration 332\u003c\/p\u003e \u003cp\u003e11.4 Linear Programming Formulation 337\u003c\/p\u003e \u003cp\u003e11.5 Approximation in Policy Space 338\u003c\/p\u003e \u003cp\u003e11.6 Appendix - Root-Finding Algorithms 342\u003c\/p\u003e \u003cp\u003e\u003cb\u003e12 System Identification 350\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e12.1 Dynamical System Models 350\u003c\/p\u003e \u003cp\u003e12.2 Regression Problem 351\u003c\/p\u003e \u003cp\u003e12.3 Input-Output Models 352\u003c\/p\u003e \u003cp\u003e12.4 Missing Data 355\u003c\/p\u003e \u003cp\u003e12.5 Nuclear Norm system Identification 357\u003c\/p\u003e \u003cp\u003e12.6 Gaussian Processes for Identification 358\u003c\/p\u003e \u003cp\u003e12.7 Recurrent Neural Networks 360\u003c\/p\u003e \u003cp\u003e12.8 Temporal Convolutional Networks 360\u003c\/p\u003e \u003cp\u003e12.9 Experiment Design 361\u003c\/p\u003e \u003cp\u003e\u003cb\u003eAppendix A 373\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003eA.1 Notation and Basic Definitions 373\u003c\/p\u003e \u003cp\u003eA.2 Software 374\u003c\/p\u003e \u003cp\u003eReferences 379\u003c\/p\u003e \u003cp\u003eIndex 387\u003c\/p\u003e","brand":"John Wiley \u0026 Sons Inc","offers":[{"title":"Default Title","offer_id":49989993562455,"sku":"9781119809135","price":88.65,"currency_code":"GBP","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0817\/1739\/5799\/files\/9781119809135.jpg?v=1739543095","url":"https:\/\/bookcurl.com\/products\/optimization-for-learning-and-control-9781119809135","provider":"Book Curl","version":"1.0","type":"link"}