A Confidence Voting Process for Ranking Problems based on Support Vector Machines (2008)
Tianshi Jiao, Jiming Peng, Tamás Terlaky
In this paper, we deal with ranking problems arising from various data mining applications where the major task is to train a rank-prediction model to assign every instance a rank. We first discuss...
Alejandro Karam, Option Méthodes, Quantitatives Gestion, C Alej, Ro Karam, ...
président-rapporteur
Approximating k-means-type clustering via semidefinite programming (2008)
One of the fundamental clustering problems is to assign n points into k clusters based on the minimal sum-of-squares(MSSC), which is known to be NP-hard. In this paper, by using matrix arguments, we...
Vikas Singh, Medical Informatics, Jiming Peng, Lopamudra Mukherjee, Jinhui Xu
pengj @ uiuc.edu
Classification with Different Models on Adult Income (2008)
squared error 109.8434 % Total Number of Instances 305 === Detailed Accuracy By Class === TP Rate FP Rate Precision Recall F-Measure Class 0.137 0.017 0.714 0.137 0.23 >50K 0.983 0.863 0.784 0.983...
New Convex Relaxations for Quadratic Assignment Problems (2008)
Jiming Peng, Hans Mittelmann, Xiaoxue Li
Quadratic assignment problems (QAPs) are known to be among the hardest discrete optimization problems. Recent study shows that even obtaining a strong lower bound for QAPs is a computational...
Tibor Ill' Es, J. Peng, C. Roos, T. Terlaky, Jiming Peng, Kees Roos, ...
We deal with Linear Complementarity Problems (LCPs) with P () matrices. First we establish the convergence rate of the complementary variables along the central path. The central path is...
Recently, in [10], the authors presented a new large-update primal-dual method for Linear Optimization, whose O(n
Tom Luo, Jiming Peng, Tamás Terlaky, J. Sturm
this paper, we study the e#ciency issue of inexact Newton-type methods for smooth unconstrained optimization problems under standard assumptions from theoretical point of view by discussing a...
Graph Modeling for Quadratic Assignment Problem Associated with the Hypercube (2007)
Hans Mittelmann, Jiming Peng, Xiaolin Wu
In the paper we consider the quadratic assignment problem arising from channel coding in communications where one coefficient matrix is the adjacency matrix of a hypercube in a finite dimensional...
A Nearly Analytical Discrete Method for Wave-Field Simulations in 2D Porous Media (2006)
Dinghui Yang, Jiming Peng, Ming Lu, Tamas Terlaky, P. R. China
Abstract. The nearly analytic discrete method (NADM) is a perturbation method originally proposed by Yang et al. (2003) [26] for acoustic and elastic waves in elastic media. This method is based on a...
A new theoretical framework for K-means-type clustering (2005)
One of the fundamental clustering problems is to assign n points into k clusters based on the minimal sum-of-squares(MSSC), which is known to be NP-hard. In this paper, by using matrix arguments, we...
On approximate balanced biclustering (2005)
Guoxuan Ma, Jiming Peng, Yu Wei
In this paper, we consider the so-called balanced bi-clustering problem for n entities in a suitable space where the number of entities in each cluster is bounded. A special case of the balanced...
Self-regular proximities and new search directions for linear and semidefinite optimization (2000)
Jiming Peng, Cornelis Roos, Tamás Terlaky
In this paper, we first introduce the notion of self-regular functions. Various appealing properties of self-regular functions are explored and we also discuss the relation between selfregular...
Self-Regular Proximities and New Search Directions for Linear and Semidefinite Optimization (2000)
Jiming Peng, Cornelis Roos, Tamás Terlaky
In this paper, we rst introduce the notion of self-regular function which is dierent from the well-known self-concordance of a function. Then we use such functions to dene proximity measures for...
A New Class of Polynomial Primal-Dual Methods for Linear and Semidefinite Optimization (2000)
Jiming Peng, Cornelis Roos, Tamás Terlaky
We propose a new class of primal-dual methods for linear optimization (LO). By using some new analysis tools, we prove that the large update method for LO based on the new search direction has a...
Department of Computing and Software, (2000)
Abstract In this paper, we first introduce the notion of self-regular function which is different from the well-known self-concordance of a function. Then we use such functions to define proximity...
A New Class of Polynomial Primal-Dual Methods for Linear and Semidefinite Optimization (1999)
Jiming Peng, Cornelis Roos, Tamás Terlaky
We propose a new class of primal-dual methods for linear optimization (LO). By using some new analysis tools, we prove that the large update method for LO based on the new search direction has a...
A New Class of Polynomial Primal-Dual Methods for Linear and Semidefinite Optimization (1999)
Jiming Peng Cornelis, Jiming Peng, Cornelis Roos
We propose a new class of primal-dual methods for linear optimization (LO). By using some new analysis tools, we prove that the large update method for LO based on the new search direction has a...
J. Peng, C. Roos, T. Terlaky, Jiming Peng, Kees Roos, Tam As Terlaky
Interior point methods for semidefinite optimization have recently been studied intensively, due to their polynomial complexity and practical efficiency. Many search directions have been proposed to...
Tibor Illes, J. Peng, C. Roos, T. Terlaky, Jiming Peng, Kees Roos, ...
We deal with Linear Complementarity Problems (LCPs) with P () matrices. First we establish the convergence rate of the complementary variables along the central path. The central path is...
Tibor Illes, Jiming Peng, Cornelis Roos, Tamas Terlaky, As Terlaky
. We deal with Linear Complementarity Problems (LCPs) with P () matrices. First we establish the convergence rate of the complementary variables along the central path. The central path is...
New Complexity Analysis of the Primal-Dual Newton Method for Linear Optimization (1998)
J. Peng, C. Roos, T. Terlaky, Jiming Peng, Cornelis Roos
We deal with the primal-dual Newton method for linear optimization (LO). Nowadays, this method is the working horse in all efficient interior point algorithms for LO, and its analysis is the basic...
New Complexity Analysis Of Primal-Dual Newtonmethods For ... Linear Complementarity Problems (1998)
Jiming Peng, Cornelis Roos, Tamás Terlaky
In this paper, we consider a primal-dual Newton method for linear complementarity problems (LCP) with P ()-matrix. By using some new analysis tools, we prove polynomial complexity of the large update...
Tibor Illes, Jiming Peng, Cornelis Roos, Tamas Terlaky, As Terlaky
We deal with Linear Complementarity Problems (LCPs) with P () matrices. First we establish the convergence rate of the complementary variables along the central path. The central path is...
New Complexity Analysis of the Primal-Dual Newton Method for Linear Optimization (1998)
J. Peng, C. Roos, T. Terlaky, Jiming Peng, Cornelis Roos
We deal with the primal-dual Newton method for linear optimization (LO). Nowadays, this method is the working horse in all efficient interior point algorithms for LO, and its analysis is the basic...
Self-adaptive support vector machines: modelling and experiments
Peng Du, Jiming Peng, Tamás Terlaky
Support vector machines (SVMs), Machine learning, Model selection, Feature selection, Bi-level programming,