%{search_type} search results

• Chapter 1. Introduction
• Chapter 2. Derivations of ADMM
• Chapter 3. ADMM for Deterministic and Convex Optimization
• Chapter 4. ADMM for Nonconvex Optimization
• Chapter 5. ADMM for Stochastic Optimization
• Chapter 6. ADMM for Distributed Optimization
• Chapter 7. Practical Issues and Conclusions.

Machine learning heavily relies on optimization algorithms to solve its learning models. Constrained problems constitute a major type of optimization problem, and the alternating direction method of multipliers (ADMM) is a commonly used algorithm to solve constrained problems, especially linearly constrained ones. Written by experts in machine learning and optimization, this is the first book providing a state-of-the-art review on ADMM under various scenarios, including deterministic and convex optimization, nonconvex optimization, stochastic optimization, and distributed optimization. Offering a rich blend of ideas, theories and proofs, the book is up-to-date and self-contained. It is an excellent reference book for users who are seeking a relatively universal algorithm for constrained problems. Graduate students or researchers can read it to grasp the frontiers of ADMM in machine learning in a short period of time.
(source: Nielsen Book Data)

• CHAPTER 1 Introduction
• CHAPTER 2 Accelerated Algorithms for Unconstrained Convex Optimization
• 1. Preliminaries
• 2. Accelerated Gradient Method for smooth optimization
• 3. Extension to the Composite Optimization
• 3.1. Nesterov's First Scheme
• 3.2. Nesterov's Second Scheme
• 3.2.1. A Primal Dual Perspective
• 3.3. Nesterov's Third Scheme
• 4. Inexact Proximal and Gradient Computing
• 4.1. Inexact Accelerated Gradient Descent
• 4.2. Inexact Accelerated Proximal Point Method
• 5. Restart
• 6. Smoothing for Nonsmooth Optimization
• 7. Higher Order Accelerated Method
• 8. Explanation: An Variational Perspective
• 8.1. Discretization
• CHAPTER 3 Accelerated Algorithms for Constrained Convex Optimization
• 1. Preliminaries
• 1.1. Case Study: Linear Equality Constraint
• 2. Accelerated Penalty Method
• 2.1. Non-strongly Convex Objectives
• 2.2. Strong Convex Objectives
• 3. Accelerated Lagrange Multiplier Method
• 3.1. Recovering the Primal Solution
• 3.2. Accelerated Augmented Lagrange Multiplier Method
• 4. Accelerated Alternating Direction Method of Multipliers
• 4.1. Non-strongly Convex and Non-smooth
• 4.2. Strongly Convex and Non-smooth
• 4.3. Non-strongly Convex and Smooth
• 4.4. Strongly Convex and Smooth
• 4.5. Non-ergodic Convergence Rate
• 4.5.1. Original ADMM
• 4.5.2. ADMM with Extrapolation and Increasing Penalty Parameter
• 5. Accelerated Primal Dual Method
• 5.1. Case 1
• 5.2. Case 2
• 5.3. Case 3
• 5.4. Case 4
• CHAPTER 4 Accelerated Algorithms for Nonconvex Optimization
• 1. Proximal Gradient with Momentum
• 1.1. Basic Assumptions
• 1.2. Convergence Theorem
• 1.3. Another Method: Monotone APG
• 2. AGD Achieves the Critical Points Quickly
• 2.1. AGD as a Convexity Monitor
• 2.2. Negative Curvature
• 2.3. Accelerating Nonconvex Optimization
• 3. AGD Escapes the Saddle Points Quickly
• 3.1. Almost Convex
• 3.2. Negative Curvature Descent
• 3.3. AGD for Non-Convex Problem
• 3.3.1. Locally Almost Convex! Globally Almost Convex
• 3.3.2. Outer Iterations
• 3.3.3. Inner Iterations
• CHAPTER 5 Accelerated Stochastic Algorithms
• 1. The Individual Convexity Case
• 1.1. Accelerated Stochastic Coordinate Descent
• 1.2. Background for Variance Reduction Methods
• 1.3. Accelerated Stochastic Variance Reduction Method
• 1.4. Black-Box Acceleration
• 2. The Individual Non-convexity Case
• 2.1. Individual Non-convex but Integrally Convex
• 3. The Non-Convexity Case
• 3.1. SPIDER
• 3.2. Momentum Acceleration
• 4. Constrained Problem
• 5. Infinity Case
• CHAPTER 6 Paralleling Algorithms
• 1. Accelerated Asynchronous Algorithms
• 1.1. Asynchronous Accelerated Gradient Descent
• 1.2. Asynchronous Accelerated Stochastic Coordinate Descent
• 2. Accelerated Distributed Algorithms
• 2.1. Centralized Topology
• 2.1.1. Large Mini-batch Algorithms
• 2.1.2. Dual Communication-Efficient Methods
• 2.2. Decentralized Topology
• CHAPTER 7 Conclusions
• APPENDIX Mathematical Preliminaries.
• (source: Nielsen Book Data)

This book on optimization includes forewords by Michael I. Jordan, Zongben Xu and Zhi-Quan Luo. Machine learning relies heavily on optimization to solve problems with its learning models, and first-order optimization algorithms are the mainstream approaches. The acceleration of first-order optimization algorithms is crucial for the efficiency of machine learning. Written by leading experts in the field, this book provides a comprehensive introduction to, and state-of-the-art review of accelerated first-order optimization algorithms for machine learning. It discusses a variety of methods, including deterministic and stochastic algorithms, where the algorithms can be synchronous or asynchronous, for unconstrained and constrained problems, which can be convex or non-convex. Offering a rich blend of ideas, theories and proofs, the book is up-to-date and self-contained. It is an excellent reference resource for users who are seeking faster optimization algorithms, as well as for graduate students and researchers wanting to grasp the frontiers of optimization in machine learning in a short time.
(source: Nielsen Book Data)

• 1. Introduction
• 2. Linear Models
• 3. Nonlinear Models
• 4. Optimization Algorithms
• 5. Representative Applications
• 6. Conclusions.
• (source: Nielsen Book Data)

Low-Rank Models in Visual Analysis: Theories, Algorithms, and Applications presents the state-of-the-art on low-rank models and their application to visual analysis. It provides insight into the ideas behind the models and their algorithms, giving details of their formulation and deduction. The main applications included are video denoising, background modeling, image alignment and rectification, motion segmentation, image segmentation and image saliency detection. Readers will learn which Low-rank models are highly useful in practice (both linear and nonlinear models), how to solve low-rank models efficiently, and how to apply low-rank models to real problems.
(source: Nielsen Book Data)

• Nary Differential Equations with Envolutionary Weights
• Infrared Image Segmentation for Photovoltaic Panels Based on Res-UNet htweight Siamese Network
• A Simple and Robust Attentional Encoder-decoder Model for License Plate Recognition
• Semi-supervised Deep Neural Networks for Object Detection in Video Surveillance Systems
• YNBIRDS: A System for Fine-grained Bird Image Recognition
• Quadratic Approximation Greedy Pursuit for Cardinality-constrained Sparse Learning
• Iterative Discriminative Domain Adaptation
• Common Structured Low-rank Matrix Recovery for Cross-view Classification
• Pruning Convolutional Neural Networks via Stochastic Gradient Hard Thresholding
• Channel and Constraint Compensation for Generative Adversarial Networks
• Faster Real-time Face Alignment Method on CPU
• A Siamese Pedestrian Alignment Network for Person Re-identification
• Training Low Bitwidth Model with Weight Normalization for Convolutional Neural Networks
• Virtual Adversarial Training on Graph Convolutional Networks in Node Classification
• Brain Functional Connectivity Augmentation Method for Mental Disease Classification with Generative Adversarial Network
• Attention-based Label Consistency for Semi-supervised Deep Learning
• Semantic Reanalysis of Scene Words in Visual Question Answering
• A Dustbin Category Based Feedback Incremental Learning Strategy for Hierarchical Image Classification
• Spatial-temporal Fusion Network with Residual Learning and Attention Mechanism: A Benchmark for Video-based Group Re-ID
• Architectural Style Classification Based on DNN Model
• DAEIMP: Denoising Autoencoder-based Imputation of Sleep Heart Health Study for Identification of Cardiovascular Diseases
• Fabric Defect Detection Based on Lightweight Neural Network
• Person Re-identification with Neural Architecture Search
• Deep Convolutional Center-based Clustering
• Exponential Moving Averaged Q-network for DDPG
• Multi-scale Convolutional Neural Network Based on 3D Context Fusion for Lesion Detection
• Orientation Adaptive YOLOv3 for Object Detection in Remote Sensing Images
• Neural Ordi.

The three-volume set LNCS 11857, 11858, and 11859 constitutes the refereed proceedings of the Second Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019, held in Xian, China, in November 2019. The 165 revised full papers presented were carefully reviewed and selected from 412 submissions. The papers have been organized in the following topical sections: Part I: Object Detection, Tracking and Recognition, Part II: Image/Video Processing and Analysis, Part III: Data Analysis and Optimization.

The three-volume set LNCS 11857, 11858, and 11859 constitutes the refereed proceedings of the Second Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019, held in Xian, China, in November 2019. The 165 revised full papers presented were carefully reviewed and selected from 412 submissions. The papers have been organized in the following topical sections: Part I: Object Detection, Tracking and Recognition, Part II: Image/Video Processing and Analysis, Part III: Data Analysis and Optimization.

The three-volume set LNCS 11857, 11858, and 11859 constitutes the refereed proceedings of the Second Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019, held in Xian, China, in November 2019. The 165 revised full papers presented were carefully reviewed and selected from 412 submissions. The papers have been organized in the following topical sections: Part I: Object Detection, Tracking and Recognition, Part II: Image/Video Processing and Analysis, Part III: Data Analysis and Optimization.