Archive for the pictures Category

what’s wrong with this picture [ans.: nothing]

Posted in Kids, pictures, Travel with tags , , , , , , , , , , on January 8, 2022 by xi'an

a journal of the plague year² [closing again]

Posted in Books, Kids, pictures, Travel, University life, Wines with tags , , , , , , , , , , , , , , on January 7, 2022 by xi'an

Had to cancel my third and final trip to Warwick this year as the Omicron scare had countries locking their borders (too late, most likely), meaning the UK was reinstating on entering travelers a self-seclusion period until the test results were known. Despite getting my third shot in time (with no side-effect whatsoever). And France retaliated in imposing PCR tests as well…

Read (over the Atlantic) an older novel of William Gibson, The Peripheral. Which is a rather standard cyberpunk Gibson with lots of (2021’s) brand names (at least at the beginning), a messy build-up of the (dual) universe, plenty of gadgets, a long-going form of fascination for super-lethal weapons and militarised survivalists, followed by a vague explanation of the temporal paradox of conversing with the future/past, and a rather lame closure with a shoot shoot bang bang resolution and some people getting absurdly rich… I am unsure I will get through the second novel, The Agency, which I bought at the same time, unless we manage to fly to French Guiana on Xmas day. Even though The Guardian is quite excited about it.

Watched Kan Eguchi’s The Fable after coming back from Mexico (not on the plane, when I slept most of the flight), which is cartoonesquely funny, except for lengthy fighting scenes. As it should, since directly inspired from a manga. While I missed the jokes about Osaka’s special dialect and food, it was absurdly funny! And fit for a particularly rainy weekend. The second installment, which I watched later, is darker and more disturbing…

Oaxaca murals [#4]

Posted in pictures, Travel with tags , , , , , on January 6, 2022 by xi'an

rentrée sur les nerfs [back to school on edge]

Posted in Kids, pictures, University life with tags , , , , , , , on January 4, 2022 by xi'an

transformation MCMC

Posted in Books, pictures, Statistics, Travel, University life with tags , , , , , , , on January 3, 2022 by xi'an

For reasons too long to describe here, I recently came across a 2013 paper by Dutta and Bhattacharya (from ISI Kolkata) entitled MCMC based on deterministic transforms, which sounded a bit dubious until I realised the deterministic label apply to the choice of the transformation and not to the Metropolis-Hastings proposal… The core of the proposed method is to make a proposal that simultaneously considers a move and its inverse, namely from x to either x’=T(x,ε) or x”=T⁻¹(x,ε) , where ε is an independent random noise, possibly degenerated to a manifold of lesser dimension. Due to the symmetry the acceptance probability is then a ratio of the target, multiplied by the x-Jacobian of T (as in reversible jump). I tried the method on a mixture of Gamma distributions target (in red) with an Exponential scale change and the resulting sample indeed fitted said target.

The authors even make an argument in favour of a unidimensional noise, although this amounts to running an implicit Gibbs sampler. Argument based on a reduced simulation cost for ε, albeit the full dimensional transform x’=T(x,ε) still requires to be computed. And as noted in the paper this also requires checking for irreducibility. The claim for higher efficiency found therein is thus mostly unsubstantiated…

“The detailed balance requirement also demands that, given x, the regions covered by the forward and the backward transformations are disjoint.”

The above statement is also surprising in that the generic detailed balance condition does not impose such a restriction.

 

%d bloggers like this: