Archive for Hungary

Hungarian Academy of Sciences under threat

Posted in Statistics with tags , , , , , , , on February 21, 2019 by xi'an

graph of the day & AI4good versus AI4bad

Posted in Books, pictures, Statistics with tags , , , , , , , , on July 15, 2018 by xi'an

Apart from the above graph from Nature, rendering in a most appalling and meaningless way the uncertainty about the number of active genes in the human genome, I read a couple of articles in this issue of Nature relating to the biases and dangers of societal algorithms. One of which sounded very close to the editorial in the New York Times on which Kristian Lum commented on this blog. With the attached snippet on what is fair and unfair (or not).

The second article was more surprising as it defended the use of algorithms for more democracy. Nothing less. Written by Wendy Tam Cho, professor of political sciences, law, statistics, and mathematics at UIUC, it argued that the software that she develops to construct electoral maps produces fair maps. Which sounds over-rosy imho, as aiming to account for all social, ethnic, income, &tc., groups, i.e., most of the axes that define a human, is meaningless, if only because the structure of these groups is not frozen in time. To state that “computers are impervious to the lure of power” is borderline ridiculous, as computers and algorithms are [so far] driven by humans. This is not to say that gerrymandering should not be fought by technological means, especially and obviously by open source algorithms, as existing proposals (discussed here) demonstrate, but to entertain the notion of a perfectly representative redistricting is not only illusory, but also far from democratic as it shies away from the one person one vote  at the basis of democracy. And the paper leaves us on the dark as to whom will decide on which group or which characteristic need be represented in the votes. Of course, this is the impression obtained by reading a one page editorial in Nature [in an overcrowded and sweltering commuter train] rather than the relevant literature. Nonetheless, I remain puzzled at why this editorial was ever published. (Speaking of democracy, the issue contains also warning reports about Hungary’s ultra-right government taking over the Hungarian Academy of Sciences.)

The Cairo Affair [book review]

Posted in Statistics with tags , , , , , , , , , , on January 28, 2017 by xi'an

After reading the Tourist trilogy, I decided to embark upon another spy novel by Steinhauer and took this book to India as another “emergency” book. Meaning as a way to escape delays and waits during our travel. While this is not a major change from the above trilogy, which I really liked, The Cairo Affair reads well and thus fits its purpose. Some of the appeal of the book is its immersion in very recent geopolitical events in Libya (far from over by now) and Egypt. (I presume there are a lot of other spy novels taking advantage of these major shifts, so this is not a major incentive for the book!) Another appeal is the connection with places I visited as a (real) tourist, from Budapest, to Croatia, to Cairo, even though I got a much more fragmented picture of the latter in the few days I spent there. While the underlying plot ends up being very thin (spoiler?!), I also liked the extreme ambiguity of the main character, whose motivations are never really revealed, possibly unknown even to herself. This major aspect of the novel makes for shortcomings on the realism plane. Worth a plane ride, definitely.

snapshot from Budapest (#5)

Posted in pictures, Running, Travel with tags , , , , , on August 4, 2013 by xi'an

IMG_0498

snapshot from Budapest (#4)

Posted in pictures, Travel with tags , , on July 30, 2013 by xi'an

DSC_5305

snapshot from Budapest (#3)

Posted in pictures, Running, Travel with tags , , , on July 28, 2013 by xi'an

IMG_0436

snapshot from Budapest (EMS 2013 #4)

Posted in pictures, Statistics, Travel, University life with tags , , , , , , on July 26, 2013 by xi'an

sunset on the Danube, Budapest, July 23, 2013Last day at EMS 2013! I started the day with an attempt to run inside the big necropolis on the east of town (Nemzeti sirkert), attempt that failed as I was too early. I then delivered my ISBA Thomas Bayes memorial lecture, with an amazing number of people (amazing conditional on the fact that it was delivered at 9am the morning after the banquet, on the last day of the conference, that it was a memorial historical talk which could be (mis-)perceived as Bayesian propaganda, and that I had put my slides on line already!). I managed (in I hope a comprehensible and not-too-boring way!) to cover most of the slides, skipping some ABC details, in the allotted hour, and not forgetting the historical note (Teller was born here) and the local ABC picture… Many aspects of past and current Bayesian statistics were missing: Fabrizio Ruggeri pointed out prior elicitation and Xiao-Li Meng [who wore a special tie with Thomas Bayes’ picture!] George Box. As an aside, has anyone versed in image analysis ever tried to link Thomas Bayes somehow doubtful portrait with his father’s? They do not look the least related to my unexpert eyes…

The rest of the day went very quickly, with a Bayesian computation session on SMC and exact approximations, and an afternoon consisting of Larry Brown’s talk on linear models as approximations (bringing a new light on the topic!) and of Xiao-Li Meng’s talk on measuring the impact of priors through a new information device. While I attended the “Future of Statistics” panel like most of the remaining participants, the future remained rather foggy, as I could not make my mind between the optimist side pointed out the growing need of statisticians at every level and the pessimist view that those jobs were mostly taken by poorly trained non-statisticians… In conclusion, I enjoyed the meeting for its diversity and range of talks, as well as its fantastic location of course!