Skip to yearly menu bar Skip to main content


Partially Exchangeable Networks and Architectures for Learning Summary Statistics in Approximate Bayesian Computation

Samuel Wiqvist · Pierre-Alexandre Mattei · Umberto Picchini · Jes Frellsen

Pacific Ballroom #87

Keywords: [ Time Series and Sequence Models ] [ Bayesian Methods ] [ Bayesian Deep Learning ] [ Approximate Inference ]


We present a novel family of deep neural architectures, named partially exchangeable networks (PENs) that leverage probabilistic symmetries. By design, PENs are invariant to block-switch transformations, which characterize the partial exchangeability properties of conditionally Markovian processes. Moreover, we show that any block-switch invariant function has a PEN-like representation. The DeepSets architecture is a special case of PEN and we can therefore also target fully exchangeable data. We employ PENs to learn summary statistics in approximate Bayesian computation (ABC). When comparing PENs to previous deep learning methods for learning summary statistics, our results are highly competitive, both considering time series and static models. Indeed, PENs provide more reliable posterior samples even when using less training data.

Live content is unavailable. Log in and register to view live content