back to Banff in 2014![14w5125]

A few days ago, we heard from BIRS‘s director the very good news, the great news, that our proposal for a workshop on Advances in Scalable Bayesian Computation had been accepted! The dates of this new workshop in Banff are March 3-7, 2014, which means 2014 will be a terrific year both for Monte Carlo-ing and for mountaineering, as it will follow MCMSki IV by two months! This proposal was led by Luke Bornn, now in Harvard, and Nando de Freitas, Scott Schmidler and myself joined forces with him. (Scott and I having the additional incentive of the prospect of terrific ice-climbing, we did not need too much prodding!) The overwhelming surroundings, the superlative facilities of the Banff Centre, and the quality of the company will undoubtedly make March 3-7, 2014, a great, great week!

Banff sunset

Banff workshop [BIRS 12w5105 meeting [#3]]

As I left Banff in the early afternoon of Thursday, I only attended the morning session of the BIRS 12w5105 workshop (just like yesterday since there was a free afternoon!). Yesterday morning, Gareth Roberts gave a brilliant talk on importance sampling for diffusions, explaining why he could use importance functions that were not absolutely continuous wrt the target distribution. I also like Jun Liu’s talk on sequential Monte Carlo. This idea of using partial or controlled rejection sampling is quite interesting indeed, even though I always wonder at why rejection is at all necessary since it introduces extra (white?) noise… Rao-Blackwellised solutions, as mentioned by Jun, should be more efficient. An issue certainly not fit for an airport lounge! This morning, the first talk by Hélène Massam was also close to my interests, since it dealt simultaneously with model choice and Bayes factors and their limit as the prior becomes improper and graphical models… I should read the recent work of Hélène on this. Her talk also mentioned the issue of computing simultaneously thousands of Bayes factors, a good challenge (even though ABC seems ill-fitted to the task). Jim Hobert gave the last talk of the morning on geometric convergence and its verification by construction a potential function: as usual, Jim’s slides were fantastically pedagogical, make sure to watch them! I am very much sorry to have missed the three afternoon talks, but will watch them over the weekend, thanks to this new incredible feature of BIRS where all videos are now on-line.

Overall, this week at BIRS, staying at the Banff Centre, and doing mountaineering, has been exhilarating if exhausting! The incredible conditions offered by the Centre go beyond the reasonable and it takes alas little time to get used to them, from the sport facilities, with my very early morning swim (6am), to the superb Sally Borden cafetaria, to the auditorium in the TransCanada Pipeline Pavilion with its video-recording facilities, and I am only sorry I could not find a climbing partner to enjoy the indoor climbing wall! Scientifically speaking, the structure of the meeting allowed for intense exchanges (even though I did not exploit those to their full extent, due to my early bedtime, trying to keep on French time, a habit which allowed me to review Pierre Simon Laplace’s book, Théorie Analytique des Probabilités, over the week, during the wee hours of the morning…, but also led to almost sure micro-naps during the talks…!)

Banff sunrise (2)

One ridge too many…

On Monday morning, Devin and I left Banff very early to try one more scramble before my plane (as the pouring rain of the previous night had killed any chance of doing real climbing). We arrived in Canmore at about 7am and hiked up to Mount Lady MacDonald, which was listed as difficult in our guidebook. The weather was very wet, if not exactly raining, and we went up in one cloud then in another. Past the abandoned structures that marked the end of the hiking trail (and the beginning of the scramble), it started to snow, although it was not feeling cold. The trail was not longer visible under the fresh wet snow and we went up the scree slope looking for the slabs indicated in the guidebook (since visibility was very poor…). We rather quickly found slabs and then faced a traverse on a narrow ridge with a knife edge, a very steep slope on one side and a vertical drop on the other side. There were footholds on the non-vertical side and by carefully moving along, sometimes in an undignified saddling fashion, we managed to (slowly) cross this ridge and to go down a dozen meters to another ridge that was announced as daunting in the guidebook. I was then convinced we were a few dozen meters from the summit, but, after reaching a second ridge, the clouds lifted to some extent, enough to see that there was still a long and exposed ridge to the true summit with at least as much snow… In fact, we had moved to the ridge too quickly and thus we were not on the scramble path! With no rope and no security point, this was getting too much of a gamble (dying for MacDonald?!) and we thus turned back for another ridge saddling… Even though we did not reach the top, this was a great scramble, most likely the most exposed I ever did!!! (Much more than the winter traverse of the Aonach Eagach, where my guide and I roped…)