Consensus-Based Distributed Support Vector Machines

By Pedro A. Forero, Alfonso Cano, Georgios B. Giannakis. 2010

429 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

DJAM: Distributed Jacobi Asynchronous Method for Learning Personal Models (2018, methodology): “Some algorithms aim at more specific optimization tasks such as distributed lasso regression [11], distributed support vector machines [12], and distributed random vector functional-link networks [13].”
Adding vs. Averaging in Distributed Primal-Dual Optimization (2015, methodology): “An alternative approach to distributed problems of our form of interest is to use the alternating direction method of multipliers (ADMM), as used for distributed SVM training e.g. in (Forero et al., 2010).”
Distributed optimization with arbitrary local solvers (2015, methodology): “Nevertheless, the method has been used for distributed SVM training in, e.g., [23].”
EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization (2014, background): “Examples and works include decentralized averaging [7,15,34], learning [9,22,26], estimation [1,2,16,18, 29], sparse optimization [19, 35], and low-rank matrix completion [20] problems.”
Distributed Alternating Direction Method of Multipliers (2012, background): “In recent works [5], [16] and [10], distributed ADMM algorithms tailored for specific machine learning problems and parameter estimation in wireless sensor networks have been proposed without convergence rate analysis.”
Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication (2018, background): “(1) The formulation (1) captures problems in sensor network, mobile computation, and multi-agent control, where either efficiently centralizing data or globally aggregate intermediate results is unfeasible (Johansson, 2008; Bullo et al., 2009; Forero et al., 2010; Ribeiro, 2010).”
Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs (2016, background): “Some examples include distributed averaging [7,50,72], distributed spectrum sensing [1], formation control [49, 58], power system control [21, 55], statistical inference and learning [20, 45, 53].”
Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms (2018, methodology): “A. Proof of Simplifying ADMM (Forero et al., 2010) By KKT condition of (5), there is: Implies: Plug (27) into (6)(7): If initialize λ aij (0) = λ bij (0) to be zero vectors for all node pairs ( i, j ) , (28 , k ∈ { a, b } will hold for all t .”
A General Analysis of the Convergence of ADMM (2015, unknown): “A partial list of examples includes Bioucas-Dias & Figueiredo (2010); Wahlberg et al. (2012); Bird (2014); Forero et al. (2010); Sedghi et al. (2014); Li Behmardi et al. (2014); Zhang & Kwok (2014).”
Finite Rate Quantized Distributed optimization with Geometric Convergence (2018, background): “Instances of (P) that fit the above distributed setting can be widely found in many applications, including network information processing and decision making [1], resource allocation in communication networks [2], distributed spectrum sensing [3], and distributed machine learning [4].”
D-ADMM: A Communication-Efficient Distributed Algorithm for Separable Optimization (2012, methodology): “The first algorithm is [16] (it also appears in [1 7], [18], [19], [20]), described in Algorithm 3.”
Privacy-Preserving Machine Learning Algorithms for Big Data Systems (2015, background): “It has been proved in [15] and [4] that the convergence of problem (14) is guaranteed as long as one of the following two conditions is true: S1 and S1 are bounded; or AA is nonsingular.”
Distributed Sparse Linear Regression (2010, background): “In other cases, such as the Internet or collaborative interlaboratory studies, agents providing private data for the purpose of ﬁtting, e.g., a sparse model, may not be willing to share their training data but only the learning results [8], [12].”
Recent Advances of Large-Scale Linear Classification (2012, background): “Examples of using ADMM for distributed training include [124].”
Distributed Multi-Task Relationship Learning (2017, background): “There have been tremendous efforts done on differentmachine learning problems [4, 13, 19].”
A Proximal Gradient Algorithm for Decentralized Composite Optimization (2015, background): “These advantages lead to successful applications of decentralized optimization in robotic networks [14], [15], wireless sensor networks [4], [16], smart grids [17], [18], and distributed machine learning systems [19], [20], just to name a few.”
Secure and resilient distributed machine learning under adversarial environments (2015, methodology): “We adopt the similar method in [9] to solve problem (25), which leads to the following result.”
Efficient Distributed Linear Classification Algorithms via the Alternating Direction Method of Multipliers (2012, methodology): “The authors in [2, 7] used the ADMM framework to solve a SVM problem in a single machine.”