Archive for Stanford University

« Older Entries

Nature tidbits [23 October 2025]

Posted in Books, Kids, pictures, Running, Travel, University life with tags , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , on November 27, 2025 by xi'an

In this October issue of nature, plenty of the “usual” topics, namely AI and Trump.2.0 wrecking balls, along with two cosmology entries that related to my trip to the early universe last week, and a pros-and-cons opposition about animal testing,

a discussion on the nature of the “little red dots” that have been recently observed and whose nature remains open, the most popular explanation (I was given during lunch) being black holes surrounded by gas (even though I cannot understand why the gas is not attracted by the black hole!) [and would have produced a more exciting cover!]

a review of the recent book Discordance: The Troubled History of the Hubble Constant by Jim Baggott, entitled Why we still don’t understand the Universe — even after a century of dispute! A review that regrets that more time is spent on the Hubble “constant” (which varies with time!) rather than more controversial issues like dark matter and dark energy (And strangely bemoans that the book is focussed on scientific developments, missing sociological ones. Duh?! (Bonus for a picture of suit-and-tie Edwin Hubble sitting at the centre of a telescope),

two entries on the well-being [or lack thereof] of PhD students, with nothing particularly surprising (eg, inclusivity and respect help!), and Brazil, Australia and Italy ranking top locations but in a comparative study that does not mention France (as often in international comparisons found in Nature) despite the place being in the top 10 countries delivering PhD degrees, not that I believe PhD students are particularly well-treated in French academia!, the (unexplained) surprise being Italy ranking so high given the close resemblance between the two countries (low stipends, shortage of postdoc and permanent positions, high teaching loads for the advisor, limited travel budgets),

a conference (purposedly) made of AI-written papers reviewed by AI referees, Agents4Science 2025, how universities are rushed into adapting to AI-fluent students, whose skills are changing, and the rise in fake authors produced by paper mills, with a limited range of acceptable solutions,

why Trump 2.0‘s blackmail on pharmaceutical companies is counter-productive and likely to slow down progress, and why his massive increase of highly qualified scientists is shooting (or nuking) USelf in the foot, given the huge proportion) of im/emigrated Nobel prize winners (for physics, chemistry, and medicine), along the (post-) Nobel prize in economics is a direct or indirect reply to this regression by awarding the Prize to economists who worked on the importance of creativity and science on growth (not very surprising at first look!)

Leave a comment »

webinar on Monte Carlo Methods

Posted in Books, Statistics, University life with tags , , , , , , , , , , , , on October 7, 2024 by xi'an


Hey, there is a new international Monte Carlo webinar starting this semester! Taking place at 8:30 am PT, 11:30 am ET (which currently set it at 16:30 in Tórshavn time and 17:30 in Longyearbyen time!). The first speakers on the list are

  1. Persi Diaconis (who gave a talk last week)
  2. Mike Giles (tomorrow!)
  3. Art Owen (on quasi-Monte Carlo)
  4. Gareth O Roberts (Warwick)

Enjoy!

Leave a comment »

repelling-attracting Hamiltonian Monte Carlo

Posted in Books, pictures, Statistics, University life with tags , , , , , , on June 25, 2024 by xi'an

Lasrt week, Siddharth Vishwanath and Hyungsuk Tak—whom I first met at an MCQMC session about multimodal sampling at MCqMC 2016 in Stanford,  same year as my San Fran’ half-marathon race, most memorable of all my races!)—proposed a Repelling-Attracting Hamiltonian Monte Carlo (raHMC) algorithm, towards sampling from multimodal distributions.

“The success of raHMC for sampling from multimodal distributions crucially hinges on the choice of the [three] tuning parameter[s]”

The concept behind raHMC is to endow an HMC algorithm with an added friction term that slows down moves, except it can get turned into an acceleration effect when the friction coefficient γ becomes negative. In a proposal remindful of leapfrog half-time moves, raHMC proceeds by switching the sign of this coefficient γ half-way of an artificial time parameter T that is representing the inter-simulation time between two successive states of the Markov chain. By this aggregation of opposite forces, the resulting algorithm satisfies the detailed-balance condition,  hence is reversible and preserves symplectic structure and volume. If not energy.

“…a direct application of the repelling-attracting mechanism to NUTS may not be straightforward. Lastly, we have not been able to guarantee that raHMC conserves energy”

Given the dependence on the tuning parameters, I fear implementing the algorithm may prove delicate in more complex settings, e.g. when the number of modes is unknown, as the acceleration component is rather blind to the actual target. In addition, the leapfrog integrator may prove quite slow in low density regions, which are visited about half the time.

“This, however, comes at the price of a higher computational cost, as the auto-tuning procedure for raHMC tends to favor longer trajectories, and therefore requires more gradient evaluations per step”

Numerical experiments show, indeed, that the algorithm is much slower than others, as this occurence of a 8.5s execution time for HMC vs a corresponding 1094s for raHM…

Leave a comment »

Bayesian goodness of fit

Posted in Books, pictures, Statistics, University life with tags , , , , , , , , , on April 10, 2018 by xi'an

 

Persi Diaconis and Guanyang Wang have just arXived an interesting reflection on the notion of Bayesian goodness of fit tests. Which is a notion that has always bothered me, in a rather positive sense (!), as

“I also have to confess at the outset to the zeal of a convert, a born again believer in stochastic methods. Last week, Dave Wright reminded me of the advice I had given a graduate student during my algebraic geometry days in the 70’s :`Good Grief, don’t waste your time studying statistics. It’s all cookbook nonsense.’ I take it back! …” David Mumford

The paper starts with a reference to David Mumford, whose paper with Wu and Zhou on exponential “maximum entropy” synthetic distributions is at the source (?) of this paper, and whose name appears in its very title: “A conversation for David Mumford”…, about his conversion from pure (algebraic) maths to applied maths. The issue of (Bayesian) goodness of fit is addressed, with card shuffling examples, the null hypothesis being that the permutation resulting from the shuffling is uniformly distributed if shuffling takes enough time. Interestingly, while the parameter space is compact as a distribution on a finite set, Lindley’s paradox still occurs, namely that the null (the permutation comes from a Uniform) is always accepted provided there is no repetition under a “flat prior”, which is the Dirichlet D(1,…,1) over all permutations. (In this finite setting an improper prior is definitely improper as it does not get proper after accounting for observations. Although I do not understand why the Jeffreys prior is not the Dirichlet(½,…,½) in this case…) When resorting to the exponential family of distributions entertained by Zhou, Wu and Mumford, including the uniform distribution as one of its members, Diaconis and Wang advocate the use of a conjugate prior (exponential family, right?!) to compute a Bayes factor that simplifies into a ratio of two intractable normalising constants. For which the authors suggest using importance sampling, thermodynamic integration, or the exchange algorithm. Except that they rely on the (dreaded) harmonic mean estimator for computing the Bayes factor in the following illustrative section! Due to the finite nature of the space, I presume this estimator still has a finite variance. (Remark 1 calls for convergence results on exchange algorithms, which can be found I think in the just as recent arXival by Christophe Andrieu and co-authors.) An interesting if rare feature of the example processed in the paper is that the sufficient statistic used for the permutation model can be directly simulated from a Multinomial distribution. This is rare as seen when considering the benchmark of Ising models, for which the summary and sufficient statistic cannot be directly simulated. (If only…!) In fine, while I enjoyed the paper a lot, I remain uncertain as to its bearings, since defining an objective alternative for the goodness-of-fit test becomes quickly challenging outside simple enough models.

Leave a comment »

Darmois, Koopman, and Pitman

Posted in Books, Statistics with tags , , , , , , , , on November 15, 2017 by xi'an

When [X’ed] seeking a simple proof of the Pitman-Koopman-Darmois lemma [that exponential families are the only types of distributions with constant support allowing for a fixed dimension sufficient statistic], I came across a 1962 Stanford technical report by Don Fraser containing a short proof of the result. Proof that I do not fully understand as it relies on the notion that the likelihood function itself is a minimal sufficient statistic.

1 Comment »

« Older Entries