Email: j.grant [at]

Twitter: @james_a_grant

Google Scholar | LinkedIn

Room A087
Science and Technology Building
Lancaster University
Lancaster, UK

I am a Research Associate at the STOR-i CDT at Lancaster University. Currently, I am focussing on sequential decision-making for recommender systems.

I recently submitted my PhD thesis, which I completed at STOR-i under the supervision of Professors David Leslie, Kevin Glazebrook and Roberto Szechtman (of the Naval Postgraduate School, USA). Previously, I have worked as a Machine Learning Research Student at My full CV is available here.

My research considers online sequential decision making for problems with complex data structures. I am particularly interested in multi-armed bandits, online optimisation, non-parametric Poisson process estimation, and recommender systems.

  • J.A. Grant, A. Boukouvalas, R. Griffiths, D.S. Leslie, S. Vakili, E. Munoz de Cote. (2019) Adaptive Sensor Placement for Continuous Spaces. In Proceedings of 36th International Conference on Machine Learning.
  • pdf | arxiv | Related material: ICML poster, ICML slides, Maths of OR slides.
  • J.A. Grant, D.S. Leslie, K. Glazebrook, R. Szechtman, A. Letchford. Adaptive Policies for Perimeter Surveillance Problems. Journal Paper in Submission.
  • draft: pdf | draft: arxiv
  • J.A. Grant, D.S. Leslie. Posterior Contraction Rates for Gaussian Cox Processes with Non-identically Distributed Data. Journal Paper in Submission.
  • draft: pdf | draft: arxiv | Related material: BNP12 Poster
  • J.A. Grant, D.S. Leslie, K. Glazebrook, R. Szechtman. (2017) Combinatorial Bandits with Filtered Feedback. Technical Report
  • arxiv