About me

I'm a PhD student in the Programming Languages Research Group at University of Bristol, supervised by Meng Wang and Roly Perera. My current research investigates the implementation and application of algebraic effects and probabilistic programming languages. My other interests include functional programming (in particular, Haskell), type-level programming, embedded domain-specific languages (eDSLs), and recursion schemes.


Research

I'm currently exploring the abstraction of algebraic effects, extensible data, and row polymorphism in probabilistic programming language design; the intention is to encode probabilistic models as first-class citizens (hence being modular and composable) whilst being simultaneously general-purpose (i.e. suitable for all forms of simulation and inference). I'm also investigating how complex inference algorithms can be modularly implemented using effect handlers as program transformations on models.

My previous work explored a structured (categorical) approach of using recursion schemes to implement neural networks, letting compositionality be promoted in new ways. In particular, I show how neural networks can be represented as fixed-points of recursive data structures, and forward and back propagation as catamorphisms (folds) and anamorphisms (unfolds) over these structures.


Papers, etc.

 Sep, 2022    Folding over Neural Networks (preprint, proceedings)
                  M.Nguyen, N.Wu
                        MPC ‘22
 Sep, 2022    Modular Probabilistic Models via Algebraic Effects (preprint, proceedings, repository)
                  M.Nguyen, R.Perera, M.Weng, N.Wu
                        ICFP ‘22
 Jan, 2022    Linked visualisations via Galois dependencies (preprint, proceedings, repository)
                  R.Perera, M.Nguyen, T.Petricek, M.Weng
                        POPL ‘22
 Sep, 2021    Composable, Modular Probabilistic Models (extended abstract, poster)
                  M.Nguyen, R.Perera, M.Weng
                        ICFP ‘21 Student Research Competition
 Aug, 2021    Composable, Modular Probabilistic Models (paper)
                  M.Nguyen, R.Perera, M.Weng
                        IFL ‘21
 Jun, 2019    Modelling Neural Networks with Recursion Schemes (dissertation, poster, repository)
                  M.Nguyen, N.Wu
                        Masters Dissertation @ University of Bristol

Talks

 Sep, 2022    Folding over Neural Networks (slides)
                       MPC ‘22
 Sep, 2022    Modular Probabilistic Models via Algebraic Effects (slides)
                       ICFP ‘22
 May, 2022    Modular Probabilistic Models via Algebraic Effects (slides)
                       PLInG Seminar @ University of Edinburgh
 Sep, 2021    Composable, Modular Probabilistic Models (video, slides)
                       ICFP ‘21 Student Research Competition
 Sep, 2021    Composable, Modular Probabilistic Models (video, slides)
                       IFL ‘21

Work

Jun '22 - Sep '22
Research Intern: Dependently typed probabilistic programming for Idris2 (repositories)
  with Ohad Kammar @ University of Edinburgh


Teaching

2019 - 2022
I give seminars and guest lectures to the Programming Languages Research Group and undergraduates @ University of Bristol.
2020 - 2021
Primary supervisor for a 4th year CS student in their masters dissertation: Deep Learning Architectures As Pure Functions @ University of Bristol.
2017 - 2020
Teaching assistant for the Functional Programming, Language Engineering, and Advanced Topics in Programming Languages units @ University of Bristol.


Awards

2021 ICFP '21 ACM Student Research Competition, 1st Place
2019 Bloomberg Award - Best Machine Learning Paper, University of Bristol
2018 Graphcore Award - Best Group Project, University of Bristol
2017 Netcraft Award - Top Ten Achieving CS Students, University of Bristol