Adam Ścibior

I am a PhD student at University of Cambridge (with Zoubin Ghahramani) and Max Planck Institute for Intelligent Systems (with Bernhard Schölkopf) as a part of the Cambridge-Tübingen PhD programme.

My research focus is on probabilistic programming, in particular on exploiting composition of Bayesian inference algorithms. I am also broadly interested in functional programming and machine learning.

Publications

• Functional programming for modular Bayesian inference
  Adam Ścibior, Ohad Kammar, and Zoubin Ghahramani
  ICFP2018

• Denotational validation of higher-order Bayesian inference
  Adam Ścibior, Ohad Kammar, Matthijs Vákár, Sam Staton, Hongseok Yang, Yufei Cai, Klaus Ostermann, Sean K. Moss, Chris Heunen, and Zoubin Ghahramani
  POPL 2018

• Consistent kernel mean estimation for functions of random variables
  Carl-Johann Simon-Gabriel*, Adam Ścibior*, Ilya Tolstikhin, and Bernhard Schölkopf
  * joint first authors
  NIPS 2016

• Fabular: regression formulas as probabilistic programming
  Johannes Borgström, Andrew D. Gordon, Long Ouyang, Claudio Russo, Adam Ścibior, and Marcin Szymczak
  POPL 2016

• Practical probabilistic programming with monads
  Adam Ścibior, Zoubin Ghahramani, and Andrew D. Gordon
  Haskell 2015

Workshop papers

• Building inference algorithms from monad transformers
  Adam Ścibior, Yufei Cai, Klaus Ostermann, and Zoubin Ghahramani
  PPS 2017

• Modular construction of Bayesian inference algorithms
  Adam Ścibior and Zoubin Ghahramani
  AABI 2016

• Parameterized probability monad
  Adam Ścibior and Adrew D. Gordon
  PPS 2016

• Reproducing kernel Hilbert space semantics for probabilistic programs
  Adam Ścibior and Bernhard Schölkopf
  PPS 2016

• Probabilistic programming with effects
  Adam Ścibior and Ohad Kammar
  HOPE 2015

Software

• monad-bayes
  a Haskell library for probabilistic programming, with an emphasis on composing inference algorithms.
• Turing
  a Julia library for probabilistic programming, with an emphasis on intuitive front-end and high performance.

Talks

• Compositional inference in probabilistic programming
  Microsoft Research Cambridge 2016

• Practical Probabilistic Programming with Monads
  Haskell Symposium 2015

• Effects in Bayesian inference
  HOPE 2015