Professor Nick Heard

Chair in Statistics

Nick
Research topics:
  • Modelling large dynamic networks
  • Statistical methods for cyber-security
  • Changepoint analysis
  • Computational Bayesian inference
  • Statistical approaches to clustering and classification
  • Meta-analysis
Contact details:
  • 543 Huxley Building
  • Department of Mathematics
  • South Kensington Campus
  • Imperial College London, SW7 2AZ
    +44 (0)20 7594 1490

Research. My main current research interests are in statistical modelling of dynamic network graphs, Gaussian process modelling, changepoint analysis and anomaly detection, with application areas including enterprise cyber-security.

Grant funding. My research activity in modelling dynamic networks is supported by an EPSRC programme grant on Network Stochastic Processes and Time Series (NeST), which is a large collaboration between Imperial, Bristol, Oxford, Bath, LSE, York. I co-lead the NeST project on Dynamic graph embeddings: procedures and inference.

Some recent publications:

  • Hallgren, K. L., Heard, N. A. and Turcotte, M. J. M. (2023) Changepoint Detection on a Graph of Time Series. Bayesian Analysis, to appear. (Open access)
  • Sanna Passino, F., Heard, N. A. and Rubin-Delanchy, P. (2022) Spectral clustering on spherical coordinates under the degree-corrected stochastic blockmodel. Technometrics, 64, 3, 346--357. (Open access)
  • Sanna Passino, F. and Heard, N. A. (2022) Latent structure blockmodels for Bayesian spectral graph clustering. Statistics and Computing, 32, 22, (Open access)
  • Heard, N. A. (2022) Standardized partial sums and products of p-values. Journal of Computational and Graphical Statistics, 31, 2, 563--573. (Open access)

PhD opportunities. I am always interested to hear from potential PhD students. Please feel free to get in touch by email to discuss potential research projects before applying.

Teaching. I teach MATH70100 Bayesian Methods and Computation, which is a compulsory module on the MSc Machine Learning and Data Science (MLDS) degree programme at Imperial. The lecture notes are taken from my textbook, An Introduction to Bayesian Inference, Methods and Computation. I am also the programme director of MSc MLDS.

Meta-Analysis
  • Heard, N. A. (2022) Standardized partial sums and products of p-values. Journal of Computational and Graphical Statistics, 31, 2, 563--573. (Open access)
  • Heard, N. A. and Rubin-Delanchy, P. T. G. (2018) Choosing Between Methods of Combining p-values. Biometrika, 105, 1, 239-246. (Online pdf)
  • Rubin-Delanchy, P. T. G., Heard, N. A. and Lawson, D. J (2018) Meta-analysis of mid-p-values: some new results based on the convex order. Journal of the American Statistical Association, 114, 527, 1105-1112. (Online pdf)
Dynamic Networks and Cyber-Security
  • Sanna Passino, F., Heard, N. A. and Rubin-Delanchy, P. (2022) Spectral clustering on spherical coordinates under the degree-corrected stochastic blockmodel. Technometrics, 64, 3, 346--357. (Open access)
  • Sanna Passino, F. and Heard, N. A. (2022) Latent structure blockmodels for Bayesian spectral graph clustering. Statistics and Computing, 32, 22, (Open access)
  • Sanna Passino, F. and Heard, N. A. (2022) Mutually exciting point process graphs for modelling dynamic networks. Journal of Computational and Graphical Statistics, 32, 1, 116--130. (Open access)
  • Sanna Passino, F., Turcotte, M. J. M. and Heard, N. A. (2022), Graph link prediction in computer networks using Poisson matrix factorisation. Annals of Applied Statistics, 16, 3, 1313--1332. (Online pdf)
  • Sanna Passino, F., Bertiger, A. S., Neil, J. C. and Heard, N. A. (2021) Link prediction in dynamic networks using random dot product graphs. Data Mining and Knowledge Discovery, 35, 2168-–2199. (Open access)
  • Sanna Passino, F. and Heard, N. A. (2020) Bayesian estimation of the latent dimension and communities in stochastic blockmodels. Statistics and Computing, 30, 5, 1291--1307. (Open access)
  • Sanna Passino, F. and Heard, N. A. (2020) Classification of periodic arrivals in event time data for filtering computer network traffic. Statistics and Computing, 30, 5, 1241--1254. (Open access)
  • Price-Williams, M. and Heard, N. A. (2020) Nonparametric Self-exciting Models for Computer Network Traffic. Statistics and Computing, 30, 2, 209-220. (Open access)
  • Sanna Passino, F. and Heard, N. A. (2019) Modelling dynamic network evolution as a Pitman-Yor process. Foundations of Data Science, 1, 3, 293-306. (Online pdf)
  • Metelli, S. and Heard, N. A. (2019) On Bayesian New Edge Prediction and Anomaly Detection in Computer Networks. Annals of Applied Statistics, 13, 4, 2586-2610. (Open access)
  • Price-Williams, M., Heard, N. A. and Rubin-Delanchy, P. (2019) Detecting weak dependence in computer network traffic patterns using higher criticism. Journal of the Royal Statistical Society, Series C, 68, 3, 641-655. (Open access)
  • Price-Williams, M., Turcotte, M. J. M. and Heard, N. A. (2018) Time of Day Anomaly Detection. In proceedings of IEEE European Intelligence and Security Informatics Conference (EISIC2018). (Open access)
  • Bolton, A. and Heard, N. A. (2018) Malware Family Discovery Using Reversible Jump MCMC Sampling of Regimes. Journal of the American Statistical Association, 113, 524, 1490-1502. (Online pdf)
  • Price-Williams, M., Heard, N. A. and Turcotte, M. J. M. (2017) Detecting periodic subsequences in cyber security data. In proceedings of IEEE European Intelligence and Security Informatics Conference (EISIC2017). (Open access)
  • Heard, N. A., Palla, K. and Skoularidou, M. (2016) Topic modelling of authentication events in an enterprise computer network. In proceedings of IEEE Intelligence and Security Informatics Conference (ISI2016), Cybersecurity and Big Data. (Open access)
  • Heard, N. A. and Rubin-Delanchy, P. T. G. (2016) Network-wide anomaly detection via the Dirichlet process. In proceedings of IEEE Big Data Analytics for Cybersecurity Computing (BDAC2016). (Open access)
  • Metelli, S and Heard, N. A. (2016) Model-Based Clustering and New Edge Modelling in Large Computer Networks. In proceedings of IEEE Intelligence and Security Informatics Conference (ISI2016), Cybersecurity and Big Data.(Open access)
  • Turcotte, M. J. M., Moore, J., Heard, N. A and McPhall, A. (2016) Poisson Factorization for Peer-Based Anomaly Detection. In proceedings of IEEE Intelligence and Security Informatics Conference (ISI2016), Cybersecurity and Big Data. (Open access)
  • Rubin-Delanchy, P. T. G., Adams N. M., and Heard, N. A. (2016) Disassortativity of computer networks. In proceedings of IEEE Big Data Analytics for Cybersecurity Computing (BDAC2016). (Open access)
  • Turcotte, M. J. M. and Heard, N. A. and Neil, J. (2014) Detecting Localised Anomalous Behaviour in a Computer Network. In Advances in Intelligent Data Analysis XIII, 321–332. (Open access)
  • Rubin-Delanchy, P. T. G. and Heard, N. A. (2014) A test for dependence between two point processes on the real line. Arxiv preprint. (Arxiv pdf)
  • Heard, N. A. and Rubin-Delanchy, P. T. G. and Lawson, D. J. (2014) Filtering automated polling traffic in computer network flow data. In proceedings of IEEE Joint Intelligence and Security Informatics Conference 2014. (Open access)
  • Metelli, S. and Heard, N. A. (2014) Modelling new edge formation in a computer network through Bayesian Variable Selection. In proceedings of IEEE Joint Intelligence and Security Informatics Conference 2014. (Open access)
  • Bolton, A. and Heard, N. A. (2014) Application of a linear time method for change point detection to the classification of software. In proceedings of IEEE Joint Intelligence and Security Informatics Conference 2014. (Open access)
  • Rubin-Delanchy, P. T. G., Lawson, D. J., Turcotte M. J. T., Adams, N. M. and Heard, N. A. (2014) Three statistical approaches to sessionizing network flow data. In proceedings of IEEE Joint Intelligence and Security Informatics Conference 2014. (Open access)
  • Lawson, D. J., Rubin-Delanchy, P. T. G. and Adams, N. M. and Heard, N. A. (2014) Statistical frameworks for detecting tunnelling in cyber defence using big data. In proceedings of IEEE Joint Intelligence and Security Informatics Conference 2014. (Online pdf)
  • Heard, N. A. and Turcotte, M. J. M. (2013). Monitoring a device in a communication network. In Data Analysis for Cyber-Security, eds. Adams, N. M. and Heard, N. A., Imperial College Press. (Online abstract)
  • Heard, N. A., Weston, D. J., Platanioti, K. and Hand, D. J. (2010) Bayesian Anomaly Detection Methods for Social Networks. Annals of Applied Statistics, 4, 2, 645-662. (Open access)
Bayesian Computation (see also Clustering)
  • Hallgren, K. L., Heard, N. A. and Turcotte, M. J. M. (2023) Changepoint Detection on a Graph of Time Series. Bayesian Analysis, to appear. (Open access)
  • Hallgren, K. L., Heard, N. A. and Adams, N. M. (2022) Changepoint detection in non-exchangeable data. Statistics and Computing, 32, 110.(Open access)
  • Heard, N. A. and Turcotte, M. J. M. (2017) Adaptive sequential Monte Carlo for multiple changepoint analysis. Journal of Computational and Graphical Statistics, 26, 2, 414-423. (Online pdf)
  • Heard, N. A. and Turcotte, M. J. M. (2016) Convergence of Monte Carlo distribution estimates from rival samplers. Statistics and Computing, 26, 6, 1147-1161. (Online pdf)
  • Holmes, C. C. and Heard, N. A. (2003) Generalized monotonic regression using random change points. Statistics in Medicine, 22, 4, 623-638. (Online pdf)
Clustering
  • Rubin-Delanchy, P., Burn, G. L., Griffie, J., Williamson, D. J., Heard, N. A., Cope, A. C. and Owen, D. M. (2015) Bayesian cluster identification in single-molecule localization microscopy data. Nature Methods, 12, 1072-1076. (Online pdf)
  • Fowler, A., Menon, A. and Heard, N. A. (2013). Dynamic Bayesian Clustering. Journal of Bioinformatics and Computational Biology, 11, 5, 1342001:1–15. (Open access)
  • Fowler, A. and Heard, N. A. (2013). Dynamic Bayesian Clustering of Gene Expression Data. In Proceedings of the 5th International Conference on Bioinformatics and Computational Biology.
  • Fowler, A. and Heard, N. A. (2012). On Two-way Bayesian Agglomerative Clustering of Gene Expression Data. Statistical Analysis and Data Mining, 5, 5, 463–476. (Online abstract)
  • Heard, N. A. (2011). Iterative Reclassification in Agglomerative Clustering. Journal of Computational and Graphical Statistics, 20, 4, 920-936. (Online pdf)
  • Heard, N. A., Holmes, C. C. and Stephens, D. A. (2006) A quantitative study of gene regulation involved in the immune response of Anopheline mosquitoes: An Application of Bayesian Hierarchical Clustering of Curves. Journal of the American Statistical Association, 101, 473, 18-29. (Online abstract)
  • Heard, N. A., Holmes, C. C., Stephens, D. A., Hand, D. J. and Dimopoulos, G. (2005) Bayesian Co-clustering of Anopheles Gene Expression Time Series: A Study of Immune Defense Response To Multiple Experimental Challenges. Proceedings of the National Academy of Science USA, 102, 47, 16939-16944. (Online abstract)
  • Hand, D. J. and Heard, N. A. (2005) Finding groups in gene expression data. Journal of Biomedicine and Biotechnology, 2, 215-225. (Online pdf)