Misclassiication Minimization
نویسنده
چکیده
The problem of minimizing the number of misclassiied points by a plane, attempting to separate two point sets with intersecting convex hulls in n-dimensional real space, is formulated as a linear program with equilibrium constraints (LPEC). This general LPEC can be converted to an exact penalty problem with a quadratic objective and linear constraints. A Frank-Wolfe-type algorithm is proposed for the penalty problem that terminates at a stationary point or a global solution. Novel aspects of the approach include: (i) A linear complementarity formulation of the step function that \counts" misclassiications, (ii) Exact penalty formulation without boundedness, nondegeneracy or constraint qualiication assumptions, (iii) An exact solution extraction from the sequence of minimizers of the penalty function for a nite value of the penalty parameter for the general LPEC and an explicitly exact solution for the LPEC with uncoupled constraints, and (iv) A parametric quadratic programming formulation of the LPEC associated with the misclassiication minimization problem.
منابع مشابه
Building Ensembles of Classi ers for Loss Minimization
One of the most active areas of research in supervised learning has been the study of methods for constructing good ensembles of classiiers, that is, a set of classi-ers whose individual decisions are combined to increase overall accuracy of classifying new examples. In many applications classiiers are required to minimize an asym-metric loss function rather than the raw misclassiication rate. ...
متن کاملBoosting Trees for Cost-Sensitive Classifications
This paper explores two boosting techniques for cost-sensitive tree classiications in the situation where misclassiication costs change very often. Ideally, one would like to have only one induction, and use the induced model for diierent misclassiication costs. Thus, it demands robustness of the induced model against cost changes. Combining multiple trees gives robust predictions against this ...
متن کاملA global optimization technique for statistical classifier design
A global optimization method is introduced for the design of statistical classiiers that minimize the rate of misclassiication. We rst derive the theoretical basis for the method, based on which we develop a novel design algorithm and demonstrate its eeectiveness and superior performance in the design of practical classiiers for some of the most popular structures currently in use. The method, ...
متن کاملOptimal Decision Trees
We propose an Extreme Point Tabu Search (EPTS) algorithm that constructs globally optimal decision trees for classiication problems. Typically, decision tree algorithms are greedy. They optimize the misclassiication error of each decision sequentially. Our non-greedy approach minimizes the misclassiication error of all the decisions in the tree concurrently. Using Global Tree Optimization (GTO)...
متن کاملHierarchical Classi cation of
Classiication is a function that matches a new object with one of the predeened classes. Document classiication is characterized by the large number of attributes involved in the objects (documents). The traditional method of building a single classiier to do all the classiica-tion work would incur a high overhead. Hierarchical classiication is a more eecient method | instead of a single classi...
متن کامل