Sparse Learning for Large-Scale and High-Dimensional Data: A Randomized Convex-Concave Optimization Approach

DOI10.1007/978-3-319-46379-7_6zbMath1478.68305arXiv1511.03766OpenAlexW2249065054MaRDI QIDQ2830269

Zhi-Hua Zhou, Tianbao Yang, Rong Jin, Li-jun Zhang

Publication date: 9 November 2016

Published in: Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1511.03766

zbMATH Keywords

random projectionsparse learningdual solutionconvex-concave optimizationprimal solution

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05) Randomized algorithms (68W20)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Smooth minimization of non-smooth functions
• Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
• User-friendly tail bounds for sums of random matrices
• Fast global convergence of gradient methods for high-dimensional statistical recovery
• Kernels as features: on kernels, margins, and low-dimensional mappings
• The restricted isometry property and its implications for compressed sensing
• Uniform uncertainty principle for Bernoulli and subgaussian ensembles
• Database-friendly random projections: Johnson-Lindenstrauss with binary coins.
• A first-order primal-dual algorithm for convex problems with applications to imaging
• An algorithmic theory of learning: Robust concepts and random projection
• One-Bit Compressed Sensing by Linear Programming
• High-dimensional subset recovery in noise: Sparsified measurements without loss of statistical efficiency
• Optimization with Sparsity-Inducing Penalties
• Random Projections for Classification: A Recovery Approach
• Robust 1-bit Compressed Sensing and Sparse Logistic Regression: A Convex Programming Approach
• Randomized Algorithms for Matrices and Data
• An Accelerated HPE-Type Algorithm for a Class of Composite Convex-Concave Saddle-Point Problems
• Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
• SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
• An elementary proof of a theorem of Johnson and Lindenstrauss
• Regularization and Variable Selection Via the Elastic Net
• Prediction, Learning, and Games

This page was built for publication: Sparse Learning for Large-Scale and High-Dimensional Data: A Randomized Convex-Concave Optimization Approach