IMPROVED PROJECTED GRADIENT ALGORITHMS FOR SINGLY LINEARLY CONSTRAINED QUADRATIC PROGRAMS SUBJECT TO LOWER AND UPPER BOUNDS
From MaRDI portal
Publication:3560109
DOI10.1142/S0217595910002594zbMath1186.90084MaRDI QIDQ3560109
Publication date: 19 May 2010
Published in: Asia-Pacific Journal of Operational Research (Search for Journal in Brave)
support vector machine (SVM); adaptive steepest descent step-size; Dai-Yuan step-size; monotone projected gradient algorithm; projection subproblem
Uses Software
Cites Work
- An O(n) algorithm for quadratic knapsack problems
- Gradient methods with adaptive step-sizes
- Monotone projected gradient methods for large-scale box-constrained quadratic programming
- An algorithm for a singly constrained class of quadratic programs subject upper and lower bounds
- Algorithms for bound constrained quadratic programming problems
- Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
- Projected Barzilai-Borwein methods for large-scale box-constrained quadratic programming
- Analysis of monotone gradient methods
- An improved gradient projection-based decomposition technique for support vector machines
- Two-Point Step Size Gradient Methods
- Quasi-Newton Updates with Bounds
- A polynomially bounded algorithm for a singly constrained quadratic program
- Inexact spectral projected gradient methods on convex sets
- Nonmonotone Spectral Projected Gradient Methods on Convex Sets
- Validation of subgradient optimization
- Gradient projection methods for quadratic programs and applications in training support vector machines
