PeopleofSuperintelligence

Researcher

Henry Reeve

Also known as Henry W. J. Reeve, Henry WJ Reeve

Henry Reeve is a researcher in statistics and machine learning whose papers cover label noise, transfer learning, multilabel classification and learning from missing data. Their degrees include a pure mathematics PhD at Bristol under Thomas Jordan and a computer science PhD at Manchester under Gavin Brown, and they did postdoctoral research at Birmingham, mentored by Ata Kabán. They were a Turing Fellow at Bristol for the 2021–2022 academic year and posted Adaptive transfer learning in 2021 with Timothy Cannings and Richard Samworth. In 2025, Score Matching with Missing Data, written with Josh Givens and Song Liu, won an Outstanding Paper Award at ICML 2025. They are an Associate Professor at the School of Artificial Intelligence at Nanjing University and an Honorary Senior Lecturer in Statistical Science at the University of Bristol.

Timeline

  1. 2010

    A pure mathematics PhD at Bristol

    They do doctoral work in pure mathematics at the University of Bristol, supervised by Thomas Jordan. In 2010, their paper on multifractal analysis for Birkhoff averages on Lalley-Gatzouras repellers appears in Fundamenta Mathematicae.

  2. 2018

    Manchester PhD and nearest-neighbour bandits

    They study for a PhD in computer science at the University of Manchester under Gavin Brown. In 2018, with Brown and Joe Mellor, they publish the k-nearest neighbour UCB algorithm for multi-armed bandits with covariates in the Algorithmic Learning Theory proceedings, with a regret bound that is minimax optimal up to logarithmic factors.

  3. 2019

    Postdoc at Birmingham

    They carry out postdoctoral research at the University of Birmingham, mentored by Ata Kabán. Their 2019 ICML paper with Kabán shows that the Robust kNN classifier reaches the minimax optimal rates of the noise-free setting, up to a log factor, when trained on data with unknown asymmetric label noise.

  4. 2021–2022

    Turing Fellow and transfer learning

    At Bristol's Institute for Statistical Science, they are named a Turing Fellow of the Alan Turing Institute for the 2021–2022 academic year. In June 2021, with Timothy Cannings and Richard Samworth, they post Adaptive transfer learning, which derives minimax optimal rates for binary classification with a related source distribution and gives an algorithm that adapts to the unknown transfer relationship. In September 2021, the same three authors post Optimal subgroup selection, which determines the minimax optimal regret for selecting a region of the feature space where a regression function exceeds a threshold.

  5. 2022

    Multilabel regret bounds at NeurIPS

    At NeurIPS 2022, they appear as a coauthor, with Róbert Busa-Fekete, Heejin Choi, Krzysztof J. Dembczynski, Claudio Gentile and Balazs Szorenyi, of Regret Bounds for Multilabel Classification in Sparse Label Regimes. The paper studies upper and lower regret bounds for Hamming loss and Precision@κ, for plug-in k-nearest-neighbour classifiers and for empirical risk minimization on surrogate losses.

  6. 2025

    ICML 2025 Outstanding Paper

    Score Matching with Missing Data, written with Josh Givens and Song Liu, wins an Outstanding Paper Award at ICML 2025 in Vancouver. The paper adapts score matching to data that are partially missing over any subset of the coordinates, with an importance weighting approach and a variational approach.

  7. January 2026

    Quantile contrasts at ICLR 2026

    In January 2026, they post Direct Doubly Robust Estimation of Conditional Quantile Contrasts with Josh Givens, Song Liu and Katarzyna Reluga, and the paper is published at ICLR 2026. It proposes the first direct estimator of the conditional quantile comparator, a quantity used in heterogeneous treatment effect analysis.

  8. As of October 2026

    Associate Professor at Nanjing

    Reeve is an Associate Professor at the School of Artificial Intelligence at Nanjing University and an Honorary Senior Lecturer in Statistical Science at the University of Bristol, where they previously worked as a Senior Lecturer. Their research is on statistics and machine learning, and they recruit PhD students for the Adaptive Non-parametric Inference and Machine Learning group at Nanjing.

Career

  1. NowNanjing UniversityAssociate Professor
  2. NowUniversity of BristolSenior Lecturer
  3. 2021–2022Alan Turing InstituteTuring Fellow
  4. From 2019University of BirminghamPostdoctoral Researcher

Education

  1. University of BristolPhD
  2. University of ManchesterPhD

From the biography.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes University of Bristol. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes University of Bristol. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Nanjing University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  4. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes University of Bristol. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Henry Reeve yet. Send us a free-licensed photo.

  1. Henry WJ Reeve henryreeve.netlify.app. Checked 21 October 2026.
  2. The K-Nearest Neighbour UCB Algorithm for Multi-Armed Bandits with Covariates proceedings.mlr.press. Checked 21 October 2026.
  3. Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noise proceedings.mlr.press. Checked 21 October 2026.
  4. Fast rates for a kNN classifier robust to unknown asymmetric label noise - University of Birmingham research.birmingham.ac.uk. Checked 21 October 2026.
  5. Six School of Mathematics academics awarded Turing Fellowship | School of Mathematics Research bristolmathsresearch.org. Checked 21 October 2026.
  6. [2106.04455] Adaptive transfer learning arxiv.org. Checked 21 October 2026.
  7. [2109.01077] Optimal subgroup selection arxiv.org. Checked 21 October 2026.
  8. Regret Bounds for Multilabel Classification in Sparse Label Regimes proceedings.neurips.cc. Checked 21 October 2026.
  9. Outstanding Paper at ICML2025 - University of Bristol research-information.bris.ac.uk. Checked 21 October 2026.
  10. ICML 2025 Awards icml.cc. Checked 21 October 2026.
  11. [2601.19666] Direct Doubly Robust Estimation of Conditional Quantile Contrasts arxiv.org. Checked 21 October 2026.
  12. Direct Doubly Robust Estimation of Conditional Quantile Contrasts proceedings.iclr.cc. Checked 21 October 2026.
  13. Dr Henry Reeve - Our People bristol.ac.uk. Checked 21 October 2026.