Hi Yogesh,
the work by John Blitzer that I mentioned used the second approach -- its
described here:
Blitzer, J., Dredze, M., Pereira, F., Jun. 2007. Biographies, bollywood,
boom-boxes and blenders: Domain adaptation for sentiment classification.
In: Proceedings of ACL, Prague, Czech Republic, pp. 440-447.
URL http://www.aclweb.org/anthology-new/P/P07/P07-1056.bib
Blitzer, J., Mcdonald, R., Pereira, F., Jul. 2006. Domain adaptation with
structural correspondence learning. In: Proceedings of the 2006 Conference
on EMNLP, Sydney, Australia, pp. 120-128.
URL http://www.cis.upenn.edu/\~{}blitzer/papers/emnlp06.pdf
he and Shai B. David did also some theoretical work that introduces the
distance I was talking about:
David, S. B., Blitzer, J., Crammer, K., Pereira, F., 2006. Analysis of
representations for domain adaptation. In: Schölkopf, B., Platt, J. C.,
Hoffman, T., Schölkopf, B., Platt, J. C., Hoffman, T. (Eds.), NIPS. MIT
Press, pp. 137-144.
URL http://dblp.uni-trier.de/rec/bibtex/conf/nips/Ben-DavidBCP06
David, S. B., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan,
J. W., May 2010. A theory of learning from different domains. Mach. Learn.
79 (1), 151-175.
URL http://dx.doi.org/10.1007/s10994-009-5152-4
I strongly recommend the book on Dataset Shift in Machine Learning edited
by Joaquin Quiñonero-Candela, Masashi Sugiyama, Anton Schwaighofer and Neil
D. Lawrence .
http://mitpress.mit.edu/books/dataset-shift-machine-learning
It contains articles from the most active researchers in the field - the
book is the result of a NIPS workshop that has been partially taped
(available on videolectures.net).
Other survey that might be helpful are:
Pan, S. J., Yang, Q., Oct. 2010. A survey on transfer learning. IEEE
Transactions on Knowledge and Data Engineering 22 (10), 1345-1359.
URL http://dx.doi.org/10.1109/tkde.2009.191
Jing Jiang, A Literature Survey on Domain Adaptation of Statistical
Classifiers,
http://sifaka.cs.uiuc.edu/jiang4/domain_adaptation/survey/da_survey.pdf
HTH,
Peter
2013/8/19 Yogesh Karpate <yogeshkarp...@gmail.com>
> Hi Folks,
> Thanks a lot for suggesting me good references!
> @ Peter : You can send me the more ref.
> @ Gael : WIsh you a speedy recovery!
> @ Olivier : Thanks a lot for listening my problem quitely and asking for
> clarifications.
> Next time and onwards I will try to be more specific explaining the
> problem!
> I will get back to you guys once I finish experiments.
>
>
> On Mon, Aug 19, 2013 at 9:12 AM, Gael Varoquaux <
> gael.varoqu...@normalesup.org> wrote:
>
>> Hi list,
>>
>> Coming back from travel, with a slight elbow injury that makes typing
>> difficult...
>>
>> Anyhow, I just wanted to stress that a lot of good advice has been
>> put forward in the discussion so far, and that, when we find time, I
>> think that a subsection of the docs dealing on class-imbalance, covariate
>> shift, domain adaption, zero-shoot learning... you name it, would be
>> useful, alongside with learning on text, or advices for big data.
>>
>> G
>>
>>
>> ------------------------------------------------------------------------------
>> Get 100% visibility into Java/.NET code with AppDynamics Lite!
>> It's a free troubleshooting tool designed for production.
>> Get down to code-level detail for bottlenecks, with <2% overhead.
>> Download for free and get started troubleshooting in minutes.
>>
>> http://pubads.g.doubleclick.net/gampad/clk?id=48897031&iu=/4140/ostg.clktrk
>> _______________________________________________
>> Scikit-learn-general mailing list
>> Scikit-learn-general@lists.sourceforge.net
>> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>>
>
>
>
> --
> Cheers!
> Yogesh Karpate
>
>
> ------------------------------------------------------------------------------
> Get 100% visibility into Java/.NET code with AppDynamics Lite!
> It's a free troubleshooting tool designed for production.
> Get down to code-level detail for bottlenecks, with <2% overhead.
> Download for free and get started troubleshooting in minutes.
> http://pubads.g.doubleclick.net/gampad/clk?id=48897031&iu=/4140/ostg.clktrk
> _______________________________________________
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
>
--
Peter Prettenhofer
------------------------------------------------------------------------------
Introducing Performance Central, a new site from SourceForge and
AppDynamics. Performance Central is your source for news, insights,
analysis and resources for efficient Application Performance Management.
Visit us today!
http://pubads.g.doubleclick.net/gampad/clk?id=48897511&iu=/4140/ostg.clktrk
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
