I am an Assistant Professor in Statistics at the Department of Mathematics & Statistics at Lancaster University. My research interests are in the mathematical foundations of Machine Learning and Statistical Learning Theory with a primary focus on devising provably effective, nonparametric algorithms for long-memory time series and multi-armed bandits, as well as on studying the possibilities and limitations of algorithmic fairness. Contact Details |
![]() |
G. Blower, A. Khaleghi, M. Kuchemann-Scales, Hasimoto frames and the Gibbs measure of periodic nonlinear Schrödinger Equation, arXiv:2205.12868, 2022.
A. Khaleghi, G. Lugosi, Inferring the mixing properties of an ergodic process, arXiv:2106.07054, 2021.
S. Grünewälder, A. Khaleghi, Oblivious Data for Fairness with Kernels, Journal of Machine Learning Research, (208): 1-36, 2021. [code]
A. Khaleghi, D. Ryabko, Clustering piecewise stationary processes, In Proceedings of the IEEE International Symposium on Information Theory, 2020. [pdf]
S. Grünewälder, A. Khaleghi, Approximations of the Restless Bandit Problem, Journal of Machine Learning Research, 20:1-37, 2019. [pdf]
A. Khaleghi, D. Ryabko, J. Mary, P. Preux, Consistent Algorithms for Clustering Time Series, Journal of Machine Learning Research, 17(3):1-32, 2016. [pdf]
A. Khaleghi, D. Ryabko, Nonparametric Multiple Change Point Estimation in Highly Dependent Time Series, Theoretical Computer Science, 620:119-133, 2016. [pdf]
A. Khaleghi, D. Ryabko, Asymptotically Consistent Estimation of the Number of Change Points in Highly Dependent Time Series In Proceedings of the International Conference on Machine Learning, 2014. [pdf][code]
A. Khaleghi, D. Ryabko, Locating Changes in Highly-Dependent Data with an Unknown Number of Change-Points, In Proceedings of Neural Information Processing Systems, 2012. [pdf] [poster][code]
A. Khaleghi, D. Ryabko, J. Mary, P. Preux, Online Clustering of Processes, In Proceedings of Artificial Intelligence & Statistics, 2012.[pdf] [poster]
A. Khaleghi, D. Silva, F. R. Kschischang, Subspace Codes, Lecture Notes in Computer Science, 2009. [pdf]
A. Khaleghi, F. R. Kschischang, Projective Space Codes for the Injection Metric, In Proceedings of the Canadian Workshop on Information Theory 2009. [pdf][poster]
Github repository for the implementation of our `algorithmically fair' classification and regression methods proposed in this paper.
On Some Unsupervised Learning Problems for Highly Dependent Time Series, PhD Thesis, INRIA Lille - Université de Lille I, 2013. [pdf]
Projective Space Codes for the Injection Metric, Masters Thesis, University of Toronto, 2009. [pdf]