Publications

[ OrcId | Semantic Scholar | Google Scholar (and why you should avoid Google Scholar) ]

Machine Learning & Probabilistic Modelling

• “Joint Non-parametric Point Process model for Treatments and Outcomes: Counterfactual Time-series Prediction Under Policy Interventions” [ preprint | arXiv/PDF ]
• “Non-separable Spatio-temporal Graph Kernels via SPDEs” [ AISTATS 2022 | arXiv/PDF ]
• “Amortized variance reduction for doubly stochastic objective” [ UAI 2020 | arXiv/PDF ]
• “Variational Gaussian process models without matrix inverses” [ AABI 2019 / PDF ]
• “Gaussian process modulated Cox processes under linear inequality constraints”
  [ AISTATS 2019 | arXiv/PDF ]
• “Learning invariances using the marginal likelihood” [ NeurIPS 2018 | arXiv/PDF ]
• “Scalable GAM using sparse variational Gaussian processes” [ AABI 2018 | arXiv/PDF ]
• “Large-scale Cox process inference using variational Fourier features” [ ICML 2018 | arXiv/PDF ]

Applications

• “Non-parametric modelling of temporal and spatial counts data from RNA-seq experiments”
  [ Bioinformatics / PDF ]
• “Many-body coarse-grained interactions using Gaussian approximation potentials”
  [ Journal of Physical Chemistry B / PDF ]
• “Spectroscopic method to measure the superfluid fraction of an ultracold atomic gas”
  [ Physical Review A 🔒 | arXiv/PDF ]

Software-related publications, Tutorials & Technical Reports

• “A tutorial on sparse Gaussian processes and variational inference” [ arXiv/PDF ]
• About GPflow: “A framework for interdomain and multioutput Gaussian processes” [ arXiv/PDF ]
• About GPflux: “A library for deep Gaussian processes” [ PROBPROG 2021 poster | arXiv/PDF ]

Ph.D. Thesis

Many-Body Coarse-Grained Interactions using Gaussian Approximation Potentials, available on arXiv.

In hindsight, I could have chosen a different name for the journal paper about the same work…