Results 1  10
of
157,282
Previous Results
"... Clustering with constraints is a developing area of machine learning. Various papers have used constraints to enforce particular clusterings, seed clustering algorithms and even learn distance functions which are then used for clustering. We present intractability results for some constraint combina ..."
Abstract

Cited by 2 (2 self)
 Add to MetaCart
Clustering with constraints is a developing area of machine learning. Various papers have used constraints to enforce particular clusterings, seed clustering algorithms and even learn distance functions which are then used for clustering. We present intractability results for some constraint
PREVIOUS RESULTS
, 1995
"... We perform new experiments on the KolmogorovSinai entropy, Lyapunov exponents, and the mean free time in billiards. We study their dependence on the geometry of the scatterers made up of two interpenetrating square lattices, each one with circular scatterers with different radius. We find, in parti ..."
Abstract
 Add to MetaCart
We perform new experiments on the KolmogorovSinai entropy, Lyapunov exponents, and the mean free time in billiards. We study their dependence on the geometry of the scatterers made up of two interpenetrating square lattices, each one with circular scatterers with different radius. We find, in particular, that the above quantities are continuous functions of the ratio of the scatterer radius. However, it seems that their derivative is discontinuous around the radius ratio which separates the diffusive and nondiffusive types of geometries.
Previous Results
, 2010
"... Zeckendorf’s Theorem Every positive integer can be written in a unique way as a sum of nonconsecutive Fibonacci numbers. 4 ..."
Abstract
 Add to MetaCart
Zeckendorf’s Theorem Every positive integer can be written in a unique way as a sum of nonconsecutive Fibonacci numbers. 4
Previous results
, 2007
"... Sharp front for the QG equation Two contour dynamics problems in incompressible flows: the Muskat problem and the QG sharp front ..."
Abstract
 Add to MetaCart
Sharp front for the QG equation Two contour dynamics problems in incompressible flows: the Muskat problem and the QG sharp front
Some optimal inapproximability results
, 2002
"... We prove optimal, up to an arbitrary ffl? 0, inapproximability results for MaxEkSat for k * 3, maximizing the number of satisfied linear equations in an overdetermined system of linear equations modulo a prime p and Set Splitting. As a consequence of these results we get improved lower bounds for ..."
Abstract

Cited by 751 (11 self)
 Add to MetaCart
We prove optimal, up to an arbitrary ffl? 0, inapproximability results for MaxEkSat for k * 3, maximizing the number of satisfied linear equations in an overdetermined system of linear equations modulo a prime p and Set Splitting. As a consequence of these results we get improved lower bounds
Learnability and the VapnikChervonenkis dimension
, 1989
"... Valiant’s learnability model is extended to learning classes of concepts defined by regions in Euclidean space E”. The methods in this paper lead to a unified treatment of some of Valiant’s results, along with previous results on distributionfree convergence of certain pattern recognition algorith ..."
Abstract

Cited by 727 (22 self)
 Add to MetaCart
Valiant’s learnability model is extended to learning classes of concepts defined by regions in Euclidean space E”. The methods in this paper lead to a unified treatment of some of Valiant’s results, along with previous results on distributionfree convergence of certain pattern recognition
Signal recovery from random measurements via Orthogonal Matching Pursuit
 IEEE TRANS. INFORM. THEORY
, 2007
"... This technical report demonstrates theoretically and empirically that a greedy algorithm called Orthogonal Matching Pursuit (OMP) can reliably recover a signal with m nonzero entries in dimension d given O(m ln d) random linear measurements of that signal. This is a massive improvement over previous ..."
Abstract

Cited by 802 (9 self)
 Add to MetaCart
previous results for OMP, which require O(m 2) measurements. The new results for OMP are comparable with recent results for another algorithm called Basis Pursuit (BP). The OMP algorithm is faster and easier to implement, which makes it an attractive alternative to BP for signal recovery problems.
Shallow Parsing with Conditional Random Fields
, 2003
"... Conditional random fields for sequence labeling offer advantages over both generative models like HMMs and classifiers applied at each sequence position. Among sequence labeling tasks in language processing, shallow parsing has received much attention, with the development of standard evaluati ..."
Abstract

Cited by 581 (8 self)
 Add to MetaCart
optimization algorithms were critical in achieving these results. We present extensive comparisons between models and training methods that confirm and strengthen previous results on shallow parsing and training methods for maximumentropy models.
Results 1  10
of
157,282