Results 1  10
of
2,139
On the optimality of the simple Bayesian classifier under zeroone loss
 MACHINE LEARNING
, 1997
"... The simple Bayesian classifier is known to be optimal when attributes are independent given the class, but the question of whether other sufficient conditions for its optimality exist has so far not been explored. Empirical results showing that it performs surprisingly well in many domains containin ..."
Abstract

Cited by 818 (27 self)
 Add to MetaCart
containing clear attribute dependences suggest that the answer to this question may be positive. This article shows that, although the Bayesian classifier’s probability estimates are only optimal under quadratic loss if the independence assumption holds, the classifier itself can be optimal under zeroone
Training Linear SVMs in Linear Time
, 2006
"... Linear Support Vector Machines (SVMs) have become one of the most prominent machine learning techniques for highdimensional sparse data commonly encountered in applications like text classification, wordsense disambiguation, and drug design. These applications involve a large number of examples n ..."
Abstract

Cited by 549 (6 self)
 Add to MetaCart
Linear Support Vector Machines (SVMs) have become one of the most prominent machine learning techniques for highdimensional sparse data commonly encountered in applications like text classification, wordsense disambiguation, and drug design. These applications involve a large number of examples n
Simultaneous Test Construction by ZeroOne
"... A method is described for simultaneous test construction using the Operations Research technique zeroone programming. The model for zeroone programming consists of two parts. The first contains the objective function that describes the aspect to be optimized. The second part contains the constrain ..."
Abstract
 Add to MetaCart
A method is described for simultaneous test construction using the Operations Research technique zeroone programming. The model for zeroone programming consists of two parts. The first contains the objective function that describes the aspect to be optimized. The second part contains
An optimal representative set selection method
 Inform. Softw. Technol
, 2000
"... The optimal representative set selection problem is defined thus: given a set of test requirements and a test suite that satisfies all test requirements, find a subset of the test suite containing a minimum number of test cases that still satisfies all test requirements. Existing methods for solving ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
for solving the representative set selection problem do not guarantee that obtained representative sets are optimal (i.e. minimal). The enhanced zero–one optimal path set selection method [C.G. Chung, J.G. Lee, An enhanced zero–one optimal path set selection method, Journal of Systems and Software, 39
Continuous Reformulations for Zero–One Programming Problems
, 2011
"... In this work, we study continuous reformulations of zero–one programming problems. We prove that, under suitable conditions, the optimal solutions of a zero–one programming problem can be obtained by solving a specific continuous problem. ..."
Abstract
 Add to MetaCart
In this work, we study continuous reformulations of zero–one programming problems. We prove that, under suitable conditions, the optimal solutions of a zero–one programming problem can be obtained by solving a specific continuous problem.
Learning kernelbased halfspaces with the zeroone loss.
 In COLT,
, 2010
"... Abstract We describe and analyze a new algorithm for agnostically learning kernelbased halfspaces with respect to the zeroone loss function. Unlike most previous formulations which rely on surrogate convex loss functions (e.g. hingeloss in SVM and logloss in logistic regression), we provide fin ..."
Abstract

Cited by 9 (2 self)
 Add to MetaCart
Abstract We describe and analyze a new algorithm for agnostically learning kernelbased halfspaces with respect to the zeroone loss function. Unlike most previous formulations which rely on surrogate convex loss functions (e.g. hingeloss in SVM and logloss in logistic regression), we provide
On Unbounded ZeroOne Knapsack with DiscreteSized Objects
"... The problem being discussed in this paper is a special case of the unbounded knapsack problem: n max zn(M) = 1 n i=1 pixi s.t. ∑n cixi ≤ β0n i=1 xi ∈ {0, 1} ∀i = 1,..., n; where pi’s are uniformly distributed random variables in [0, 1], cis are discrete random variables distributed uniformly in {1/ ..."
Abstract
 Add to MetaCart
/M, 2/M,..., (M − 1)/M, 1} and zn(M) is the optimal objective function value. 2β0 Assuming that M is large, zn(M) approximately equals to
ON UNBOUNDED ZEROONE KNAPSACK WITH DISCRETESIZED OBJECTS
"... This paper presents an approximated solution for an unbounded knapsack problem where the sizes of objects are discrete values: max zn(M) = 1 n∑ pixi n i=1 n∑ s.t. cixi ≤ β0n i=1 xi ∈{0, 1} ∀i =1,...,n where pis are the profits that are uniformly distributed random variables in [0,1]. The sizes cis ..."
Abstract
 Add to MetaCart
are discrete random variables which are distributed uniformly in {1/M, 2/M,...,(M − 1)/M, 1}. zn(M) is the total profit to be maximized. Assuming that M is large, it is found that the optimal profit zn(M) is approximately equal to 2β0/3(1 − 0.3062 ( √ β0M) −1). An example from auction is used to explain
A Polynomial Case of Unconstrained ZeroOne Quadratic Optimization
, 2001
"... Unconstrained zeroone quadratic maximization problems can be solved in polynomial time when the symmetric matrix describing the objective function is positive semidefinite of fixed rank with known spectral decomposition. ..."
Abstract

Cited by 18 (0 self)
 Add to MetaCart
Unconstrained zeroone quadratic maximization problems can be solved in polynomial time when the symmetric matrix describing the objective function is positive semidefinite of fixed rank with known spectral decomposition.
On the optimality of multiantenna broadcast scheduling using zeroforcing beamforming
 IEEE J. SELECT. AREAS COMMUN
, 2006
"... Although the capacity of multipleinput/multipleoutput (MIMO) broadcast channels (BCs) can be achieved by dirty paper coding (DPC), it is difficult to implement in practical systems. This paper investigates if, for a large number of users, simpler schemes can achieve the same performance. Specifica ..."
Abstract

Cited by 308 (4 self)
 Add to MetaCart
. Specifically, we show that a zeroforcing beamforming (ZFBF) strategy, while generally suboptimal, can achieve the same asymptotic sum capacity as that of DPC, as the number of users goes to infinity. In proving this asymptotic result, we provide an algorithm for determining which users should be active under
Results 1  10
of
2,139