Results 1  10
of
171
Evidence for Invariants in Local Search
 IN PROCEEDINGS OF AAAI97
, 1997
"... It is well known that the performance of a stochastic local search procedure depends upon the setting of its noise parameter, and that the optimal setting varies with the problem distribution. It is therefore desirable to develop general priniciples for tuning the procedures. We present two statisti ..."
Abstract

Cited by 183 (11 self)
 Add to MetaCart
It is well known that the performance of a stochastic local search procedure depends upon the setting of its noise parameter, and that the optimal setting varies with the problem distribution. It is therefore desirable to develop general priniciples for tuning the procedures. We present two statistical measures of the local search process that allow one to quickly find the optimal noise settings. These properties are independent of the fine details of the local search strategies, and appear to be relatively independent of the structure of the problem domains. We applied these principles to the problem of evaluating new search heuristics, and discovered two promising new strategies.
On Network Correlated Data Gathering
 IN IEEE INFOCOM
, 2004
"... We consider the problem of correlated data gathering by a network with a sink node and a tree communication structure, where the goal is to minimize the total transmission cost of transporting the information collected by the nodes, to the sink node. Two coding strategies are analyzed: a SlepianWolf ..."
Abstract

Cited by 98 (9 self)
 Add to MetaCart
We consider the problem of correlated data gathering by a network with a sink node and a tree communication structure, where the goal is to minimize the total transmission cost of transporting the information collected by the nodes, to the sink node. Two coding strategies are analyzed: a SlepianWolf model where optimal coding is complex and transmission optimization is simple, and a joint entropy coding model with explicit communication where coding is simple and transmission optimization is difficult. This problem requires a joint optimization of the rate allocation at the nodes and of the transmission structure. For the SlepianWolf setting, we derive a closed form solution and an efficient distributed approximation algorithm with a good performance. For the explicit communication case, we prove that building an optimal data gathering tree is NPcomplete and we propose various distributed approximation algorithms.
Unsupervised Texture Segmentation in a Deterministic Annealing Framework
, 1998
"... We present a novel optimization framework for unsupervised texture segmentation that relies on statistical tests as a measure of homogeneity. Texture segmentation is formulated as a data clustering problem based on sparse proximity data. Dissimilarities of pairs of textured regions are computed from ..."
Abstract

Cited by 91 (9 self)
 Add to MetaCart
We present a novel optimization framework for unsupervised texture segmentation that relies on statistical tests as a measure of homogeneity. Texture segmentation is formulated as a data clustering problem based on sparse proximity data. Dissimilarities of pairs of textured regions are computed from a multiscale Gabor filter image representation. We discuss and compare a class of clustering objective functions which is systematically derived from invariance principles. As a general optimization framework we propose deterministic annealing based on a meanfield approximation. The canonical way to derive clustering algorithms within this framework as well as an efficient implementation of meanfield annealing and the closely related Gibbs sampler are presented. We apply both annealing variants to Brodatzlike microtexture mixtures and realword images.
VLSI cell placement techniques
 ACM Computing Surveys
, 1991
"... VLSI cell placement problem is known to be NP complete. A wide repertoire of heuristic algorithms exists in the literature for efficiently arranging the logic cells on a VLSI chip. The objective of this paper is to present a comprehensive survey of the various cell placement techniques, with emphasi ..."
Abstract

Cited by 75 (0 self)
 Add to MetaCart
VLSI cell placement problem is known to be NP complete. A wide repertoire of heuristic algorithms exists in the literature for efficiently arranging the logic cells on a VLSI chip. The objective of this paper is to present a comprehensive survey of the various cell placement techniques, with emphasis on standard ce11and macro
Parallel Recombinative Simulated Annealing: A Genetic Algorithm
, 1995
"... This paper introduces and analyzes a parallel method of simulated annealing. Borrowing from genetic algorithms, an effective combination of simulated annealing and genetic algorithms, called parallel recombinative simulated annealing, is developed. This new algorithm strives to retain the desirable ..."
Abstract

Cited by 74 (3 self)
 Add to MetaCart
This paper introduces and analyzes a parallel method of simulated annealing. Borrowing from genetic algorithms, an effective combination of simulated annealing and genetic algorithms, called parallel recombinative simulated annealing, is developed. This new algorithm strives to retain the desirable asymptotic convergence properties of simulated annealing, while adding the populations approach and recombinative power of genetic algorithms. The algorithm iterates a population of solutions rather than a single solution, employing a binary recombination operator as well as a unary neighborhood operator. Proofs of global convergence are given for two variations of the algorithm. Convergence behavior is examined, and empirical distributions are compared to Boltzmann distributions. Parallel recombinative simulated annealing is amenable to straightforward implementation on SIMD, MIMD, or sharedmemory machines. The algorithm, implemented on the CM5, is run repeatedly on two deceptive problems...
Semisupervised Learning of Classifiers: Theory, Algorithms and Their Application to HumanComputer Interaction
 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
, 2004
"... Automatic classification is one of the basic tasks required in any pattern recognition and human computer interaction application. In this paper we discuss training probabilistic classifiers with labeled and unlabeled data. We provide a new analysis that shows under what conditions unlabeled data ..."
Abstract

Cited by 59 (15 self)
 Add to MetaCart
Automatic classification is one of the basic tasks required in any pattern recognition and human computer interaction application. In this paper we discuss training probabilistic classifiers with labeled and unlabeled data. We provide a new analysis that shows under what conditions unlabeled data can be used in learning to improve classification performance. We also show that if the conditions are violated, using unlabeled data can be detrimental to classification performance. We discuss the implications of this analysis to a specific type of probabilistic classifiers, Bayesian networks, and propose a new structure learning algorithm that can utilize unlabeled data to improve classification. Finally, we show how the resulting algorithms are successfully employed in two applications related to humancomputer interaction and pattern recognition; facial expression recognition and face detection.
Combinatorial preconditioners for sparse, symmetric, diagonally dominant linear systems
, 1996
"... ..."
A Distributed CSMA Algorithm for Throughput and Utility Maximization in Wireless Networks
"... In multihop wireless networks, designing distributed scheduling algorithms to achieve the maximal throughput is a challenging problem because of the complex interference constraints among different links. Traditional maximalweight (MW) scheduling, although throughputoptimal, is difficult to imple ..."
Abstract

Cited by 57 (7 self)
 Add to MetaCart
In multihop wireless networks, designing distributed scheduling algorithms to achieve the maximal throughput is a challenging problem because of the complex interference constraints among different links. Traditional maximalweight (MW) scheduling, although throughputoptimal, is difficult to implement in distributed networks; whereas a distributed greedy protocol similar to IEEE 802.11 does not guarantee the maximal throughput. In this paper, we introduce an adaptive CSMA scheduling algorithm that can achieve the maximal throughput distributedly under some assumptions. Major advantages of the algorithm include: (1) It applies to a very general interference model; (2) It is simple, distributed and asynchronous. Furthermore, we combine the algorithm with endtoend flow control to achieve the optimal utility and fairness of competing flows. The effectiveness of the algorithm is verified by simulations. Finally, we consider some implementation issues in the setting of 802.11 networks.
A Bayesian Approach to Dynamic Contours through Stochastic Sampling and Simulated Annealing
 IEEE Trans. Pattern Analysis and Machine Intelligence
, 1994
"... In many applications of image analysis, simply connected objects are to be located in noisy images. During the last 56 years active contour models have become popular for finding the contours of such objects. Connected to these models are iterative algorithms for finding the minimizing energy curve ..."
Abstract

Cited by 55 (1 self)
 Add to MetaCart
In many applications of image analysis, simply connected objects are to be located in noisy images. During the last 56 years active contour models have become popular for finding the contours of such objects. Connected to these models are iterative algorithms for finding the minimizing energy curves making the curves behave dynamically through the iterations. These approaches do however have several disadvantages. The numerical algorithms that are in use constraint the models that can be used. Furthermore, in many cases only local minima can be achieved.