Hello, Thank you very much for your comments! I will remove the part about the windowing optimizations (though, that was my favourite part :) ), and think about what other statistics could be added. And thank you for the link with the collection of many relevant algorithms, they are very interesting!
Best regards, Gabor 2015-03-26 17:35 GMT-05:00 Paris Carbone <par...@kth.se>: > Hi Gabor, > > Approximate statistics is a really good topic, I think there is a lot to do > if you focus there. One idea would also be to include some of your > contributions to the incremental machine learning library that will be > available by June. From there you will be able to also use sampling and > stream mining primitives out-of-the-box among others. Regarding window > optimisations, as Gyula said, there is not much to do simply because we are > working heavily on it already. Good luck and thanks for the proposal! > > Paris > >> On 26 Mar 2015, at 22:59, Gyula Fóra <gyula.f...@gmail.com> wrote: >> >> Hey Gabor, >> >> Thank you for the proposal. It has many interesting ideas and a good >> potential. >> >> My comments: >> >> We already have a large amount of ongoing work on the windowing >> optimizations, covering your suggestions in section 1. It would be better >> to drop that part from the project because thats very heavily on the >> research side and as I said we are working on this at SICS. >> >> I like the list that you made for section 2., and this should be the main >> emphasis on the project. It would indeed be very nice to have a wide range >> of statistics that we can compute (or approximate - this should be optional >> thoug) on streams and windows (maybe we should also add some practical >> stuff like top-k, distinct etc). >> >> Here is a list of interesting papers that seems to be related to this >> project >> >> https://gist.github.com/debasishg/8172796 >> >> Cheers, >> Gyula >> >> On Thu, Mar 26, 2015 at 7:50 PM, Gábor Gévay <gga...@gmail.com> wrote: >> >>> Hello, >>> >>> I will be applying to the Google Summer of Code, and I wrote most of >>> the proposal: >>> http://compalg.inf.elte.hu/~ggevay/Proposal.pdf >>> I would appreciate it if you could comment on it. >>> >>> Gyula Fora, git blame is telling me that you wrote most of the >>> relevant parts of the windowing code, so I would be especially >>> interested in what you think of my improvement ideas. >>> >>> Best regards, >>> Gabor >>> >
