Category Archives: Uncategorized

Exoplanetary atmosphere retrieval: still not distinguishing between generalities and specifics

I noticed a recent arXival by the group using random forests to approximate Bayesian posteriors from pre-computed model grids of exoplanetary atmosphere (or, this time, brown dwarf) spectra.  Once again I feel that there remains a fundamental misunderstanding of the … Continue reading

Posted in Uncategorized | Leave a comment

Everyone wants a pop at the champ (part 1) …

One of the downsides of leading research in a particular field—which is what the Malaria Atlas Project team does w.r.t. probabilistic risk mapping of malaria burden—is that certain other research groups inevitably get tired of playing catch up and start … Continue reading

Posted in Uncategorized | Leave a comment

Dataset splitting to probe misspecification …

A recent arXival motivated by CMB experiment posteriors presents a heuristic for understanding the expected degree to which adding new data should reshape the posterior of a well-specified model (under the ‘nice’ scenario that the experimental data overwhelms the influence … Continue reading

Posted in Uncategorized | Leave a comment

A game of telephone …

An arXival from today has made me even more skeptical of the value of this notion of splitting machine learning uncertainty into the so-called aleatoric and epistemic contributions a la Kendall & Gal (2017): aleatoric = “noise inherent in the … Continue reading

Posted in Uncategorized | Leave a comment

Oxford institutions are institutionally racist

I noticed this article in the Grauniad today, about a blind Ghanaian student dragged by his ankles from the Oxford Union chamber.  Having spent over 5 years working at the University of Oxford now it is my firm impression that the … Continue reading

Posted in Uncategorized | Leave a comment

A novel approach to likelihood-free inference: just use the likelihood!

A new arXival describes “a novel inference framework based on Approximate Bayesian Computation” for a modelling exercise in the field of strong gravitational lensing.  Since they acknowledge insightful discussions from the guys who seem to deliberate refuse to cite my … Continue reading

Posted in Uncategorized | Leave a comment

More dumping on the NeurIPS Bayesian Deep Learning Workshop …

Today I noticed another paper on astro ph that irked me, and again it turns out to be accepted at this year’s NeurIPS Bayesian Deep Learning Workshop.  This particular arXival proposes to explore a Bayesian approach to construction of super-resolution … Continue reading

Posted in Uncategorized | Leave a comment