Subgradient method
Subgradient methods are iterative methods for solving convex minimization problems. Originally developed by Naum Z. Shor and others in the 1960s and 1970s, subgradient methods are convergent when applied even to a non-differentiable objective function. When the objective function is differentiable, sub-gradient methods for unconstrained problems use the same search direction as the method of steepest descent. Subgradient projection methods are often applied to large-scale problems with decomposition techniques. Such decomposition methods often allow a simple distributed method for a problem.
known for
Wikipage redirect
Bundle methodClaude LemaréchalConvex optimizationCutting-plane methodDerivative-free optimizationDimitri BertsekasDrift plus penaltyLasso (statistics)List of numerical analysis topicsLoss functions for classificationMathematical optimizationNaum Z. ShorNewton's methodNonsmooth minimizationOptimal designQuasiconvex functionRegularization (mathematics)Stochastic gradient descentSubderivativeSubgradient methodsSupport-vector machine
Link from a Wikipage to another Wikipage
known for
seeAlso
primaryTopic
Subgradient method
Subgradient methods are iterative methods for solving convex minimization problems. Originally developed by Naum Z. Shor and others in the 1960s and 1970s, subgradient methods are convergent when applied even to a non-differentiable objective function. When the objective function is differentiable, sub-gradient methods for unconstrained problems use the same search direction as the method of steepest descent. Subgradient projection methods are often applied to large-scale problems with decomposition techniques. Such decomposition methods often allow a simple distributed method for a problem.
has abstract
Subgradient methods are iterat ...... tributed method for a problem.
@en
Субградиентные методы — итерат ...... й распределённый метод задачи.
@ru
Субградієнтні методи - це ітер ...... зподілений метод для проблеми.
@uk
次梯度法是求解凸函数最优化(凸优化)问题的一种迭代法。次梯度 ...... 将次梯度法与分解技术结合,有时能够开发出问题的简单分配算法。
@zh
Wikipage page ID
page length (characters) of wiki page
Wikipage revision ID
1,021,719,420
Link from a Wikipage to another Wikipage
wikiPageUsesTemplate
hypernym
type
comment
Subgradient methods are iterat ...... tributed method for a problem.
@en
Субградиентные методы — итерат ...... й распределённый метод задачи.
@ru
Субградієнтні методи - це ітер ...... зподілений метод для проблеми.
@uk
次梯度法是求解凸函数最优化(凸优化)问题的一种迭代法。次梯度 ...... 将次梯度法与分解技术结合,有时能够开发出问题的简单分配算法。
@zh
label
Subgradient method
@en
Субградиентные методы
@ru
Субградієнтний метод
@uk
次梯度法
@zh