Recent Advances of Large-Scale Linear Classification

By Guo-Xun Yuan, Chia-Hua Ho, Chih-Jen Lin. Proceedings of the IEEE, 2012

306 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/588647becf62d068010cb1230c4486cbfbee642d

How researchers see this paper

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

In Artificial Intelligence

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Distributed Box-Constrained Quadratic Optimization for Dual Linear SVM (2015, unknown): “It is well-known that instead of directly solving (1), optimizing its dual problem shown below is sometimes faster (Hsieh et al., 2008; Yuan et al., 2012), especially when l < n, because there are fewer variables to optimize.”
Substructure counting graph kernels for machine learning from RDF data (2015, background): “More recently, interest has increased for large scale linear classification [7] for larger datasets, for which a number of graph kernels can also be used.”
Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function (2011, background): “While they seem to have never belonged to the mainstream focus of the optimization community, a renewed interest in CD methods wa sparked recently by their successful application in several areas—training support vector machines in machine learning [5], [3], [18], [28], [29], optimization [9], [23],”
Distributed coordinate descent for generalized linear models with regularization (2016, background): “For several problems the testing accuracy has shown to be close to that of nonlinear kernel methods [5].”
Randomness in neural networks: an overview (2017, background): “hinge loss) are possible, but do not admit a closed-form solution anymore; a review on recent progress for large-scale linear classification is given by Yuan et al.(26) While this is enough to implement a working RW-FNN in most situations, it only scratches the surface of all possible modifications ”
Large-scale logistic regression and linear support vector machines using spark (2014, methodology): “…ching-pei@cs.wisc.edu 1210 W. Dayton St. +1-812-269-6958 Madison, WI 53706, USA http://pages.cs.wisc.edu/~ching-pei Research Interest • Efficient methods for large-scale nonlinear optimization • Theoretical analysis of optimization algorithms Education University of Wisconsin-Madison, WI, USA • Ph.”
Applications of Deep Learning and Reinforcement Learning to Biological Data (2017, methodology): “Popular supervised methods include: Artificial Neural Network (ANN) [13] and its variants, Support Vector Machines [14] and linear classifiers [15], Bayesian Statistics [16], k-Nearest Neighbors [17], Hidden Markov Model [18], and Decision Trees [19].”
Kernel Methods and Machine Learning (2014, background): “More generally, for some recent advances of large-scale linear classification, see [101, 314].”
Distributed optimization with arbitrary local solvers (2015, unknown): “The dual optimization problem for formulation (1) —as a special case of Fenchel duality —can be written as follows [61, 77]: max α∈Rn { D(α) := 1 n ( ∑n i=1 − `i (−αi))− λg∗ ( 1 λnXα )} , (2) where X = [x1,x2, .”
A second-order method for strongly convex ℓ1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _1$$\end{document}-re (2013, background): “For more details about support vector machine problems we refer the reader to [33].”
Stochastic, Distributed and Federated Optimization for Machine Learning (2017, background): “1)—as a special case of Fenchel duality— can be written as follows [192, 164]:”