## enjoy a cuppa for International Tea Day

Posted in Mountains, pictures, Travel, Wines with tags , , , , , , , , , , on May 21, 2020 by xi'an

## Castleton second flush 2018

Posted in Mountains, pictures, Travel with tags , , , , , , , on October 18, 2018 by xi'an

After receiving an email from the tea dealers Nathmulls in the town of Darjeeling for an offer of the latest summer harvest of F.T.G.F.O.P. Castleton tea, I made a join order of two kilos for my te-addicted colleagues in the maths department in Dauphine, delivery that I found in my office this morning. Truly terrific tea, at about a fifth of the price asked by the major tea chain in Paris!

## optimal Bernoulli factory

Posted in Statistics with tags , , , , , , , , , , on January 17, 2017 by xi'an

One of the last arXivals of the year was this paper by Luis Mendo on an optimal algorithm for Bernoulli factory (or Lovàsz‘s or yet Basu‘s) problems, i.e., for producing an unbiased estimate of f(p), 0<p<1, from an unrestricted number of Bernoulli trials with probability p of heads. (See, e.g., Mark Huber’s recent book for background.) This paper drove me to read an older 1999 unpublished document by Wästlund, unpublished because of the overlap with Keane and O’Brien (1994). One interesting gem in this document is that Wästlund produces a Bernoulli factory for the function f(p)=√p, which is not of considerable interest per se, but which was proposed to me as a puzzle by Professor Sinha during my visit to the Department of Statistics at the University of Calcutta. Based on his 1979 paper with P.K. Banerjee. The algorithm is based on a stopping rule N: throw a fair coin until the number of heads n+1 is greater than the number of tails n. The event N=2n+1 occurs with probability

${2n \choose n} \big/ 2^{2n+1}$

[Using a biased coin with probability p to simulate a fair coin is straightforward.] Then flip the original coin n+1 times and produce a result of 1 if at least one toss gives heads. This happens with probability √p.

Mendo generalises Wästlund‘s algorithm to functions expressed as a power series in (1-p)

$f(p)=1-\sum_{i=1}^\infty c_i(1-p)^i$

with the sum of the weights being equal to one. This means proceeding through Bernoulli B(p) generations until one realisation is one or a probability

$c_i\big/1-\sum_{j=1}^{i-1}c_j$

event occurs [which can be derived from a Bernoulli B(p) sequence]. Furthermore, this version achieves asymptotic optimality in the number of tosses, thanks to a form of Cramer-Rao lower bound. (Which makes yet another connection with Kolkata!)

## incredible India

Posted in Kids, Mountains, pictures, Running, Travel with tags , , , , , , , , , , , , , , on January 15, 2017 by xi'an

[The following is a long and fairly naïve rant about India and its contradiction, without pretence at anything else than writing down some impressions from my last trip. JATP: Just another tourist post!]

Incredible India (or Incredible !ndia) is the slogan chosen by the Indian Ministry of Tourism to promote India. And it is indeed an incredible country, from its incredibly diverse landscapes [and not only the Himalayas!] and eco-systems, to its incredibly huge range of languages [although I found out during this trip that the differences between Urdu and Hindi are more communitarian and religious than linguistic, as they both derive from Hindustani, although the alphabets completely differ] and religions [a mixed blessing], to its incredibly rich history and culture, to its incredibly wide offer of local cuisines [as shown by the Bengali sample below, where the mustard seed fish cooked in banana leaves and the fried banana flowers are not visible!] and even wines [like Sula Vineyards, which offers a pretty nice Viognier]. Not to mention incredibly savoury teas from Darjeeling and Assam. Continue reading

## empirical Bayes, reference priors, entropy & EM

Posted in Mountains, Statistics, Travel, University life with tags , , , , , , , , , , , on January 9, 2017 by xi'an

Klebanov and co-authors from Berlin arXived this paper a few weeks ago and it took me a quiet evening in Darjeeling to read it. It starts with the premises that led Robbins to introduce empirical Bayes in 1956 (although the paper does not appear in the references), where repeated experiments with different parameters are run. Except that it turns non-parametric in estimating the prior. And to avoid resorting to the non-parametric MLE, which is the empirical distribution, it adds a smoothness penalty function to the picture. (Warning: I am not a big fan of non-parametric MLE!) The idea seems to have been Good’s, who acknowledged using the entropy as penalty is missing in terms of reparameterisation invariance. Hence the authors suggest instead to use as penalty function on the prior a joint relative entropy on both the parameter and the prior, which amounts to the average of the Kullback-Leibler divergence between the sampling distribution and the predictive based on the prior. Which is then independent of the parameterisation. And of the dominating measure. This is the only tangible connection with reference priors found in the paper.

The authors then introduce a non-parametric EM algorithm, where the unknown prior becomes the “parameter” and the M step means optimising an entropy in terms of this prior. With an infinite amount of data, the true prior (meaning the overall distribution of the genuine parameters in this repeated experiment framework) is a fixed point of the algorithm. However, it seems that the only way it can be implemented is via discretisation of the parameter space, which opens a whole Pandora box of issues, from discretisation size to dimensionality problems. And to motivating the approach by regularisation arguments, since the final product remains an atomic distribution.

While the alternative of estimating the marginal density of the data by kernels and then aiming at the closest entropy prior is discussed, I find it surprising that the paper does not consider the rather natural of setting a prior on the prior, e.g. via Dirichlet processes.