Online Linear Optimization with Sparsity Constraints
ثبت نشده
چکیده
We study the problem of online linear optimization with sparsity constraints in the 1 semi-bandit setting. It can be seen as a marriage between two well-known problems: 2 the online linear optimization problem and the combinatorial bandit problem. For 3 this problem, we provide two algorithms which are efficient and achieve sublinear 4 regret bounds. Moreover, we extend our results to two generalized settings, one 5 with delayed feedbacks and one with costs for receiving feedbacks. Finally, we 6 conduct experiments which show the effectiveness of our methods in practice. 7
منابع مشابه
Online Linear Optimization with Sparsity Constraints
We study the problem of online linear optimization with sparsity constraints in the 1 semi-bandit setting. It can be seen as a marriage between two well-known problems: 2 the online linear optimization problem and the combinatorial bandit problem. For 3 this problem, we provide two algorithms which are efficient and achieve sublinear 4 regret bounds. Moreover, we extend our results to two gener...
متن کاملControl Problems with Equality Constraints
not available at time of publication. Dimitris Bertsimas Massachusetts Insitute of Technology [email protected] MS8 Less is More: Robustness and Sparsity in Multivariate Statistics We describe applications of robust optimization in the context of machine learning, with a focus on classification and regression, principal component analysis and fitting of graphical models. In these tasks, sparsity...
متن کاملStructural Properties of Affine Sparsity Constraints
We introduce a new constraint system for sparse variable selection in statistical learning. Such a system arises when there are logical conditions on the sparsity of certain unknown model parameters that need to be incorporated into their selection process. Formally, extending a cardinality constraint, an affine sparsity constraint (ASC) is defined by a linear inequality with two sets of variab...
متن کاملRule Weight Optimization and Feature Selection in Fuzzy Systems with Sparsity Contraints
In this paper, we are dealing with a novel data-driven learning method (SparseFIS) for Takagi-Sugeno fuzzy systems, extended by including rule weights. Our learning method consists of three phases: the first phase conducts a clustering process in the input/output feature space with iterative vector quantization. Hereby, the number of clusters = rules is pre-defined and denotes a kind of upper b...
متن کاملOPTIMIZATION OF LINEAR OBJECTIVE FUNCTION SUBJECT TO FUZZY RELATION INEQUALITIES CONSTRAINTS WITH MAX-AVERAGE COMPOSITION
In this paper, the finitely many constraints of a fuzzy relationinequalities problem are studied and the linear objective function on the regiondefined by a fuzzy max-average operator is optimized. A new simplificationtechnique which accelerates the resolution of the problem by removing thecomponents having no effect on the solution process is given together with analgorithm and a numerical exa...
متن کامل