position at UBC

The Department of Statistics at the University of British Columbia, Vancouver invites applications from outstanding new investigators for a tenure-track position at the rank of Assistant Professor in the area of statistical machine learning and artificial intelligence (AI), with an anticipated start date of July 1, 2022 or January 1, 2023.

This position is offered as part of a new, interdisciplinary research cluster, AI Methods for Scientific Impact (AIM-SI) within UBC’s Centre for AI Decision-making and Action (CAIDA). CAIDA consists of over 100 researchers whose research leverages AI; AIM-SI will hire 5 new faculty members across three departments: Computer Science, Mathematics, and Statistics. Those recruited will join over a dozen existing researchers who are highly active in the core AI Methods research community.

Candidates must have a Ph.D. in Statistics, Biostatistics, or a related field and must demonstrate evidence of research success and a high potential to be leaders in their research field. The successful candidate should have a strong record of research productivity commensurate with their experience and will be expected to develop an independent research program in an area that complements existing Department expertise and aligns with opportunities at UBC. The successful candidate will be expected to effectively supervise Statistics graduate students, collaborate with other faculty members, obtain external funding, teach undergraduate and graduate Statistics courses, and actively participate in departmental activities.

Equity and diversity are essential to academic excellence. An open and diverse community fosters the inclusion of voices that have been underrepresented or discouraged. We encourage applications from members of groups that have been marginalized on any grounds enumerated under the B.C. Human Rights Code, including sex, sexual orientation, gender identity or expression, racialization, disability, political belief, religion, marital or family status, age, and/or status as a First Nation, Métis, Inuit, or Indigenous person.

Applicants will be asked to complete an equity survey. The survey information will not be used to determine eligibility for employment, but will be collated to provide data that can assist us in understanding the diversity of our applicant pool and identifying potential barriers to the employment of designated equity group members. Applicants’ participation in the survey is voluntary and confidential and takes only a minute to complete. Applicants may self-identify in one or more of the designated equity groups, or may also decline to identify in any or all of the questions by choosing “not disclosed.”

All qualified candidates are encouraged to apply; however, Canadians and permanent residents will be given priority.

Deadline for application is December 15. More information is available at

https://www.stat.ubc.ca/assistant-professor-aim-si-tenure-track-position

parallel tempering on optimised paths

Saifuddin Syed, Vittorio Romaniello, Trevor Campbell, and Alexandre Bouchard-Côté, whom I met and discussed with on my “last” trip to UBC, on December 2019, just arXived a paper on parallel tempering (PT), making the choice of tempering path an optimisation problem. They address the touchy issue of designing a sequence of tempered targets when the starting distribution π⁰, eg the prior, and the final distribution π¹, eg the posterior, are hugely different, eg almost singular.

“…theoretical analysis of reversible variants of PT has shown that adding too many intermediate chains can actually deteriorate performance (…) [while] on non reversible regime adding more chains is guaranteed to improve performances.”

The above applies to geometric combinations of π⁰ and π¹. Which “suffers from an arbitrarily suboptimal global communication barrier“, according to the authors (although the counterexample is not completely convincing since π⁰ and π¹ share the same variance). They propose a more non-linear form of tempering with constraints on the dependence of the powers on the temperature t∈(0,1).  Defining the global communication barrier as an average over temperatures of the rejection rate, the path characteristics (e.g., the coefficients of a spline function) can then be optimised in terms of this objective. And the temperature schedule is derived from the fact that the non-asymptotic round trip rate is maximized when the rejection rates are all equal. (As a side item, the technique exposed in the earlier tempering paper by Syed et al. was recently exploited for a night high resolution imaging of a black hole from the M87 galaxy.)

emergence [jatp]

 

 

 

midnight run

off to Vancouver

Today I am flying to Vancouver for an ABC workshop, the second Symposium on Advances in Approximate Bayesian Inference, which is a pre-NeurIPS workshop following five earlier editions, to some of which I took part. With an intense and exciting programme. Not attending the following NeurIPS as I had not submitted any paper (and was not considering relying on a lottery!). Instead, I will give a talk at ABC UBC on Monday 4pm, as, coincidence, coincidence!, I was independently invited by UBC to the IAM-PIMS Distinguished Colloquium series. Speaking on ABC on a broader scale than in the workshop. Where I will focus on ABC-Gibbs. (With alas no time for climbing, missing an opportunity for a winter attempt at The Stawamus Chief!)