Search results

Abstract Probabilistic programming is the idea of writing models from statistics and machine learning using program notations and reasoning about these models using generic inference engines. Recently its combination with deep learning has been explored …

Abstract Probabilistic and differentiable programming paradigms are being adopted by the scientific community, promising major advances in simulation pipelines, data analysis, and design optimization of experiments. This talk will cover ongoing work in …

Abstract The subtle semantics of probabilistic programs makes it difficult to correctly compile them. Moreover, because many inference algorithms for probabilistic programs are approximate and randomized, detecting miscompilation bugs is challenging. This …

Abstract In this talk, I give a brief and gentle introduction to Sequential Monte Carlo methods (with a particular focus on sequential inference in state-space models), I discuss the potential connections with probabilistic programming (from the …

Abstract H. G. Wells wrote: "Statistical thinking will one day be as necessary for efficient citizenship as the ability to read and write!" The main thread of this talk argues that statistical thinking is transforming programming language research. It is …

Chair : Hélène Rey (LBS) …