搜索结果: 1-12 共查到“Convexity”相关记录12条 . 查询时间(0.046 秒)
A Simple Condition for the Convexity of Optimal Control over Networks with Delays
Convexity Delays
2015/6/19
We consider the problem of multiple subsystems, each with its own controller, such that the dynamics of each subsystem may affect those of other subsystems with some propagation delays, and the contro...
Convexity of Optimal Control over Networks with Delays and Arbitrary Topology
Delays Arbitrary Topology
2015/6/19
We consider the design of optimal controllers for a networked system (or a spatio-temporal system), where the dynamics of each subsystem may affect those of other subsystems with some propagation dela...
Quadratic Invariance is Necessary and Sufficient for Convexity
Convexity Necessary and Sufficient
2015/6/19
In decentralized control problems, a standard approach is to specify the set of allowable decentralized controllers as a closed subspace of linear operators. This then induces a corresponding set of o...
In decentralized control problems, a standard approach is to specify the set of allowable decentralized controllers as a closed subspace of linear operators. This then induces a corresponding set of Y...
Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression
Adaptivity averaged stochastic gradient descent local strong convexity logistic regression
2013/4/28
In this paper, we consider supervised learning problems such as logistic regression and study the stochastic gradient method with averaging, in the usual stochastic approximation setting where observa...
Neyman-Pearson classification, convexity and stochastic constraints
binary classifi cation Neyman-Pearson paradigm anomaly detection stochastic constraint convexity empirical risk minimization chance constrained optimization
2011/3/25
Motivated by problems of anomaly detection, this paper implements the Neyman-Pearson paradigm to deal with asymmetric errors in binary classification with a convex loss. Given a finite collection of c...
Addendum to: An Approach to Hierarchical Clustering via Level Surfaces and Convexity
Hierarchical Clustering Level Sets Level Surfaces Radial Basis Function Convex Heat Gravity Light Cluster Validation Ridge Path Euclidean Distance Manhattan Distance Metric
2013/1/29
This article is an addendum to the 2001 paper [1] which investigated an approach to hierarchical clustering based on the level sets of a density function induced on data points in a d-dimensional feat...
On the Non-Convexity of the Time Constant in First-Passage Percolation
First-passage percolation timeconstant convexity
2009/5/11
We give a counterexample to a conjecture of Hammersley and Welsh (1965) about the convexity of the time constant in first-passage percolation, as a functional on the space of distribution functions. T...
Brownian couplings,convexity,and shy-ness
Brownian motion co-adapted coupling convexity coupling Markovian coupling perverse coupling stochastic differential
2009/5/7
Benjamini, Burdzy and Chen (2007) introduced the notion of a shy coupling: a coupling of a Markov process such that, for suitable starting points, there is a positive chance of the two component proce...
Brownian couplings, convexity, and shy-ness
Brownian motion co-adapted coupling convexity coupling Markovian coupling perversecoupling reflection coupling
2009/4/29
Benjamini, Burdzy and Chen (2007) introduced the notion of a shy coupling: a coupling of a Markov process such that, for suitable starting points, there is a positive chance of the two component proce...
Benjamini, Burdzy and Chen (2007) introduced the notion of a shy coupling: a coupling of a Markov process such that, for suitable starting points, there is a positive chance of the two component proce...
THE CONVERGENCE OF BROYDEN ALGORITHMS WITHOUT CONVEXITY ASSUMPTION
Broyden algorithms convergence convexi
2007/12/10
摘要 In this paper we discuss the convergence of the Broyden algorithms without convexity and exact line search assumptions. We proved that if the objective function is suitably smooth and the algorithm...