Natural statistical science [#1]

is it necessary to learn summary statistics? [One World ABC seminar]

Next week, on 30 November, at 9am (UK time), Yanzhi Chen (Cambridge) will give a One World ABC webinar on Is “It Necessary to Learn Summary Statistics for Likelihood-free Inference?”, a PMLR paper join with Michael Guttman and Adrian Weller:

Likelihood-free inference (LFI) is a set of techniques for inference in implicit statistical models. A longstanding question in LFI has been how to design or learn good summary statistics of data, but this might now seem unnecessary due to the advent of recent end-to- end (i.e. neural network-based) LFI methods. In this work, we rethink this question with a new method for learning summary statistics. We show that learning sufficient statistics may be easier than direct posterior inference, as the former problem can be reduced to a set of low-dimensional, easy-to-solve learning problems. This suggests us to explicitly decouple summary statistics learning from posterior inference in LFI. Experiments on five inference tasks with different data types validate our hypothesis.

 

Calyampudi Radhakrishna Rao (1920-2023)

Just heard that C.R. Rao had passed away on Wednesday. Above is a 1941 picture I photographed while attending the jubilee of the Department of Statistics of the University of Calcuta. Showing R.A. Fisher and P.C. Mahalanobis surrounded by faculty and students from the Department. Including a very young Rao who would a few years later go to Cambridge and write a PhD thesis on ANOVA under the supervision of R.A. Fisher. While my own interactions with C.R. Rao have been quite limited, from attending a seminar dinner with him when he visited Purdue University in 1988, to writing a critical assessment of Pitman nearness that he reportedly disliked, to writing chapters in some of the handbooks he edited and a review paper on Rao-Blackwellisation for the International Statistical Review special issue for his 100th birthday (which almost coincided with mine, one day off), he stood as a giant of the field, having impacted statistics and beyond in many and profound ways. The Hindu published an obituary immediately after his death, while Current Science has a longer if older biography full of pictures and Significance a series of articles on “C.R. Rao’s Century”. However, I’d like to recall this quote of his’, acknowledging his mother for his work habits.

‘For instilling in me the quest for knowledge, I owe to my mother, A. Laxmikanthamma, who, in my younger days, woke me up every day at four in the morning and lit the oil lamp for me to study in the quiet hours of the morning when the mind is fresh.’

CIRM, Luminy, 1995

Brexit and ERC funding

The Guardian posted Brexit causes collapse in European research funding for Oxbridge last weekend, yet another article on the negative impact of Brexit (or rather of the non-implementation of the Northern Ireland agreement) on UK research (and in particular Oxford and Cambridge), with the rather obvious remark that hardly any UK-based researcher is now receiving ERC funding. Actually, the only exception (mentioned in the article) happens to be an ERC-Synergy grant where the Oxford team is the only non-EU team in the synergy. This is not the case for our own OCEAN project, where Gareth Roberts at Warwick is funded by the compensation fund set (for now) by the UK Government. The article also mentions that, out of the 150 ERC grants allotted to UK-based researchers last year, about one in eight was activated by the rewarded researcher leaving the UK research sytem. Along with the collapse in foreign students attending UK universities (presumably moving to collapsing further since Sunak’s current government considers them as immigration figures to be curbed!), this state of affairs confirms the degree of absurdity of Brexit, undoubtedly the worst political move of the Century!