the sky [isn’t] the limit

early morn in Powys [jatp]

Metropolis-Hastings via classification

Veronicka Rockova (from Chicago Booth) gave a talk on this theme at the Oxford Stats seminar this afternoon. Starting with a survey of ABC, synthetic likelihoods, and pseudo-marginals, to motivate her approach via GANs, learning an approximation of the likelihood from the GAN discriminator. Her explanation for the GAN type estimate was crystal clear and made me wonder at the connection with Geyer’s 1994 logistic estimator of the likelihood (a form of discriminator with a fixed generator). She also expressed the ABC approximation hence created as the actual posterior times an exponential tilt. Which she proved is of order 1/n. And that a random variant of the algorithm (where the shift is averaged) is unbiased. Most interestingly requiring no calibration and no tolerance. Except indirectly when building the discriminator. And no summary statistic. Noteworthy tension between correct shape and correct location.

X de Sceaux 2018 [20:25, 14/185, 2/21]

Without any preparation [apart from my daily jog], I signed for the 5k in my local park, two days before the race, the 43rd trail of Sceaux. As it had snowed a lot in the past week, the race was mostly on (in?) slush, if not overly slippery, the remaining part being enjoyably muddy! I did a fairly poor time but still managed to squeeze in between the first and the third runners in my V2 (Grand Masters) category. With a 4 seconds differential each time!