Louis Sharrock

Lecturer in Statistical Science

profile-pic-2.jpeg

Dept. of Statistical Science

University College London

1-19 Torrington Place

London, WC1E 7HB

About. I am a Lecturer (Assistant Professor) in the Department of Statistical Science at University College London. I was previously a Senior Research Associate with Prof. Chris Nemeth at Lancaster University, and a Data Science Heilbronn Research Fellow at the University of Bristol. I obtained my PhD in the Department of Mathematics at Imperial College London, supervised by Dr. Nikolas Kantas. I also hold an MRes in Mathematics and an MSc in Statistics from Imperial College London, and an MA in Mathematics from the University of Cambridge.

Research. My research interests lie at the intersection of computational statistics, machine learning, and optimisation, with a particular focus on the design and analysis of scalable algorithms for statistical inference in complex statistical models. My current research focuses on the development of learning-rate-free sampling algorithms, the application of score-based diffusion models to likelihood-free inference, and the design of efficient methods for online parameter estimation in interacting particle systems and mean-field equations.

Supervision. I welcome inquiries from motivated students interested in pursuing a PhD. If you are interested in working with me, I encourage you to take a closer look at my publication list and get in touch if you see a good fit. Further information for prospective students is available here.

news

Jun 2, 2025 I have just started a new position as Lecturer (Assistant Professor) in the Department of Statistical Science at University College London.
Nov 24, 2024 In Jun 2025, I will give an invited talk at the Isaac Newton Institute workshop on Accelerating statistical inference and experimental design with machine learning.
Oct 7, 2024 Our paper - “Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows” - has been accepted to NeurIPS 2024!
May 23, 2024 We have a new preprint on “Markovian Flow Matching” on the arXiv! Check it out here.
May 1, 2024 Our paper - “Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds” - has also been accepted as a spotlight at ICML 2024!
May 1, 2024 Our paper - “Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models” - has been accepted as a spotlight at ICML 2024!
Jan 19, 2024 Our paper - “Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin Betting” - has been accepted to AISTATS 2024!
Oct 20, 2023 We are organising an exciting workshop at the RSS on Gradient Flows for Sampling, Inference, and Learning. Click here for more details.
Sep 21, 2023 Our paper - “Learning Rate Free Sampling in Constrained Domains” - has been accepted to NeurIPS 2023!
Sep 8, 2023 In Feb 2024, I will give an invited talk on parameter-free optimisation on the space of probability measures at ISMP 2024.
Aug 14, 2023 In Feb 2024, I will give an invited talk on online parameter estimation for interacting particle systems at the SIAM Conference on Uncertainty Quantification.
May 24, 2023 We have two new preprints up on arXiv! Check them out here and here.

selected publications

  1. Online Parameter Estimation for the McKean-Vlasov Stochastic Differential Equation
    Stochastic Processes and their Applications, 2023
  2. Two-timescale stochastic gradient descent in continuous time with applications to joint online parameter estimation and optimal sensor placement
    Louis Sharrock, and Nikolas Kantas
    Bernoulli, 2023
  3. Coin Sampling: Gradient-Based Bayesian Inference without Learning Rates
    Louis Sharrock, and Christopher Nemeth
    Proceedings of the 40th International Conference on Machine Learning (ICML 2023), 2023
  4. Learning Rate Free Sampling in Constrained Domains
    Louis SharrockLester Mackey, and Christopher Nemeth
    Proceedings of the 37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023), 2023
  5. AISTATS
    Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin Betting
    Louis SharrockDaniel Dodd, and Christopher Nemeth
    Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024), 2024
  6. Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Models
    Louis SharrockJack SimonsSong Liu, and Mark Beaumont
    Proceedings of the 41st International Conference on Machine Learning (ICML 2024), 2024