Archive for AISTATS 2014
skyndimynd frá Íslandi (#6)
Posted in Kids, Mountains, pictures, Running, Travel with tags AISTATS 2014, geese, Iceland, Reykjavik, sea, sunset on April 27, 2014 by xi'an
Le Monde puzzle [#869]
Posted in Books, Kids, R, Statistics, University life with tags AISTATS 2014, Le Monde, mathematical puzzle, R, Reykjavik, sapply(), sudoku, unique() on April 27, 2014 by xi'anA Le Monde mathematical puzzle once again in a Sudoku mode:
In an nxn table, all integers between 1 and n appear n times. If max denotes the maximum over the numbers of different integers on all rows and columns, what is the minimum value of max when n=7? when n=11?
I tried to solve it by the following R code (in a pre-breakfast mode in my Reykjavik Airbnb flat!):
[sourcecode language=”r” gutter=”false”]
#pseudoku
n=7
T=10^4
vals=rep(1:n,n)
minmax=n
for (t in 1:T){
psudo=matrix(sample(vals),ncol=n)
maxc=maxr=max(sapply(apply(psudo,1,unique),length))
if (maxc<minmax)
maxr=max(sapply(apply(psudo,2,unique),length))
minmax=min(minmax,max(maxc,maxr))
}
[/sourcecode]
but later realised that (a) the
sapply(apply(psudo,1,unique),length)
failed when all rows or all columns had the same number of unique terms and (b) I did not have to run the whole matrix:
[sourcecode language=”r” gutter=”false”]
vals=rep(1:n,n)
minmax=n
for (t in 1:T){
psudo=matrix(sample(vals),ncol=n)
maxc=max(length(unique(psudo[1,])),length(unique(psudo[,1])))
i=1
while((i<n)&(maxc<minmax)){
i=i+1
maxc=max(maxc,
length(unique(psudo[i,])),
length(unique(psudo[,i])))}
minmax=min(minmax,maxc)
}
[/sourcecode]
gaining a factor of 3 in the R execution. With this random exploration, the minimum value returned was 2,2,2,3,4,5,5,6,7,8 for n=2,3,4,5,6,7,8,9,10,11. Half-hearted simulating annealing during one of the sessions of AISTATS 2014 did not show any difference…
skyndimynd frá Íslandi (#5)
Posted in Mountains, pictures, Running, Travel with tags AISTATS 2014, Esja, Iceland, Reykjavik, waterfront on April 26, 2014 by xi'an
AISTATS 2014 / MLSS tutorial
Posted in Mountains, R, Statistics, University life with tags ABC, ABC model choice, AISTATS 2014, Berder, Brittany, Iceland, machine learning, MLSS, Reykjavik, summary statistics, Vannes on April 26, 2014 by xi'anHere are the slides of the tutorial on ABC methods I gave yesterday at both AISTAST 2014 and MLSS. (I actually gave a tutorial at another MLSS a few years ago, on the pretty island of Berder in Brittany, next to Vannes.) They are definitely similar to previous talks and tutorials I delivered on this topic of ABC algorithms, with only the last part being original (if unpublished yet). And even then: as Michael Gutmann from the University of Helsinki pointed out to me at the end of my talk, there are similarities between the classification method he exposed at MCMSki 4 in Chamonix and our use of random forests. Before my talk, I attended the tutorial of Roderick Murray-Smith from the University of Glasgow, on Machine learning and Human Computer Interaction, which was just stunning in its breadth, range of applications, and mastering of multimedia tools. Making me feel like a perfectly inadequate follower…
[speakerdeck https://speakerdeck.com/xianblog/mlss-tutorial%5D
skyndimynd frá Íslandi (#4)
Posted in Mountains, pictures, Travel with tags AISTATS 2014, Esja, Iceland, Reykjavik, sunset, volcanoes on April 25, 2014 by xi'an
