BibSonomy publications for /author/Dayanik

]> BibSonomy publications for /author/Dayanik http://www.bibsonomy.org/burst/author/Dayanik BibSonomy BuRST Feed for /author/Dayanik 2008-10-12T00:10:32+02:00 On the optimal stopping problem for one-dimensional diffusions Stochastic Processes and their Applicationshttp://www.bibsonomy.org/bibtex/274981add796d2e38210a8d0a44d352fc/smicha smicha 2008-04-22T14:25:45+02:00 Optimal stopping

On the optimal stopping problem for one-dimensional diffusions

Savas Dayanik and Ioannis Karatzas Stochastic Processes and their Applications 107 173--212 (2003)

to Optimal stopping by smicha on 2008-04-22 14:25:45 ]]> Stochastic Processes and their ApplicationsOct2173--212On the optimal stopping problem for one-dimensional diffusions1072003Optimal stopping 2008-04-22 14:25:45.0 The standard Poisson disorder problem revisited Stochastic Processes and their Applicationshttp://www.bibsonomy.org/bibtex/25e69823697bf49f9bb7c8ad73c1da1a3/smicha smicha 2008-04-22T14:25:45+02:00 Poisson disorder problem

The standard Poisson disorder problem revisited

Erhan Bayraktar and Savas Dayanik and Ioannis Karatzas Stochastic Processes and their Applications 115 1437--1450 (2005)

to Poisson disorder problem by smicha on 2008-04-22 14:25:45 ]]> Stochastic Processes and their ApplicationsSep91437--1450The standard Poisson disorder problem revisited1152005Poisson disorder problem 2008-04-22 14:25:45.0 Sequential testing of simple hypotheses about compound Poisson processes Stochastic Processes and their Applicationshttp://www.bibsonomy.org/bibtex/24fc52c21c6eac896936329aef8bbe3db/smicha smicha 2008-04-22T14:25:45+02:00 Sequential hypothesis testing

Sequential testing of simple hypotheses about compound Poisson processes

Savas Dayanik and Semih O. Sezer Stochastic Processes and their Applications 116 1892--1919 (2006)

to Sequential hypothesis testing by smicha on 2008-04-22 14:25:45 ]]> Stochastic Processes and their ApplicationsDec121892--1919Sequential testing of simple hypotheses about compound Poisson processes1162006Sequential hypothesis testing 2008-04-22 14:25:45.0 Bayesian sequential change diagnosis dblphttp://www.bibsonomy.org/bibtex/20be4ad777c4bacddbdeaf34c9cb911e0/dblp dblp 2008-01-02T00:00:00+01:00 dblp

Bayesian sequential change diagnosis

Savas Dayanik and Christian Goulding and H. Vincent Poor CoRR abs/0710.4847 (2007)

to dblp by dblp on 2008-01-02 00:00:00 ]]> CoRRinformal publicationBayesian sequential change diagnosisabs/0710.48472007dblp 2008-01-02 00:00:00.0 Multisource Bayesian sequential change detection dblphttp://www.bibsonomy.org/bibtex/2073ceb2feefffce3bdac484c7fdacb7c/dblp dblp 2008-01-02T00:00:00+01:00 dblp

Multisource Bayesian sequential change detection

Savas Dayanik and Harold Vincent Poor and Semih Onur Sezer CoRR abs/0708.0224 (2007)

to dblp by dblp on 2008-01-02 00:00:00 ]]> CoRRinformal publicationMultisource Bayesian sequential change detectionabs/0708.02242007dblp 2008-01-02 00:00:00.0 Adaptive Poisson disorder problem dblphttp://www.bibsonomy.org/bibtex/28682d5a1188dd37db05fcd62d62b2c1a/dblp dblp 2008-01-02T00:00:00+01:00 dblp

Adaptive Poisson disorder problem

Erhan Bayraktar and Savas Dayanik and Ioannis Karatzas CoRR abs/math/0610184 (2006)

to dblp by dblp on 2008-01-02 00:00:00 ]]> CoRRinformal publicationAdaptive Poisson disorder problemabs/math/06101842006dblp 2008-01-02 00:00:00.0 Joint Detection and Identification of an Unobservable Change in the Distribution of a Random Sequence dblphttp://www.bibsonomy.org/bibtex/2777b52f10dae3381b52dd13211036d07/dblp dblp 2008-01-02T00:00:00+01:00 dblp

Joint Detection and Identification of an Unobservable Change in the Distribution of a Random Sequence

Savas Dayanik and Christian Goulding and H. Vincent Poor CoRR abs/0705.0043 (2007)

to dblp by dblp on 2008-01-02 00:00:00 ]]> CoRRinformal publicationJoint Detection and Identification of an Unobservable Change in the Distribution of a Random Sequenceabs/0705.00432007dblp 2008-01-02 00:00:00.0 Using Text Classifiers for Numerical Classification. http://www.bibsonomy.org/bibtex/25b25c6b148179c71721ab8574f83b467/jil jil 2007-12-13T22:47:18+01:00 dichte feature mdl numeric split

Using Text Classifiers for Numerical Classification.

Sofus A. Macskassy and Haym Hirsh and Arunava Banerjee and Aynur A. Dayanik IJCAI 885-890 (2001)

to dichte feature mdl numeric split by jil on 2007-12-13 22:47:18 ]]> IJCAIconf/ijcai/2001885-890Using Text Classifiers for Numerical Classification.2001dichte feature mdl numeric split 2007-12-13 22:47:18.0 Joint Detection and Identification of an Unobservable Change in the Distribution of a Random Sequence. dblphttp://www.bibsonomy.org/bibtex/25c58440aa1790a0dc921460dd13cb350/dblp dblp 2007-09-07T00:00:00+02:00 dblp

Joint Detection and Identification of an Unobservable Change in the Distribution of a Random Sequence.

Savas Dayanik and Christian Goulding and H. Vincent Poor CISS 68-73 (2007)

to dblp by dblp on 2007-09-07 00:00:00 ]]> CISSconf/ciss/200768-73Joint Detection and Identification of an Unobservable Change in the Distribution of a Random Sequence.2007dblp 2007-09-07 00:00:00.0 Constructing informative prior distributions from domain knowledge in text classification. http://www.bibsonomy.org/bibtex/2635997d34b77c2dde18c229867257017/flawed flawed 2007-05-30T18:43:30+02:00 classification priors

Constructing informative prior distributions from domain knowledge in text classification.

Aynur A. Dayanik and David D. Lewis and David Madigan and Vladimir Menkov and Alexander Genkin SIGIR 493-500 (2006)

to classification priors by flawed on 2007-05-30 18:43:30 ]]> SIGIRconf/sigir/2006493-500Constructing informative prior distributions from domain knowledge in text classification.2006classification priors 2007-05-30 18:43:30.0 Supervised learning approaches to text classification are in practice often required to work with small and unsystematically collected training sets. The alternative to supervised learning is usually viewed to be building classifiers by hand, using a domain expert's understanding of which features of the text are related to the class of interest. This is expensive, requires a degree of sophistication about linguistics and classification, and makes it difficult to use combinations of weak predictors. We propose instead combining domain knowledge with training examples in a Bayesian framework. Domain knowledge is used to specify a prior distribution for the parameters of a logistic regression model, and labeled training data is used to produce a posterior distribution, whose mode we take as the final classifier. We show on three text categorization data sets that this approach can rescue what would otherwise be disastrously bad training situations, producing much more effective classifiers.