Personal profile
Personal profile
Azadeh Khaleghi is a Professor of Statistics at ENSAE - CREST. She earned her Ph.D. in Mathematics from Université de Lille I - INRIA Lille (France) and holds an M.Sc. and B.Sc. in Electrical and Computer Engineering from the University of Toronto. Her research focuses on the mathematical foundations of statistics and machine learning, emphasizing long-memory and mixing processes. She develops nonparametric methods for estimating mixing coefficients, modelling complex dependencies in time series, and designing statistical learning and sequential decision-making algorithms robust to long-range dependencies and non-stationarities. Her techniques for understanding dependence in stochastic processes also inform broader areas of statistical learning, including algorithmic fairness.
Research interests
statistical learning theory, information theory, nonparametric statistics, long-memory processes
Fingerprint
- 1 Similar Profiles
Collaborations and top research areas from the last five years
-
Estimating the Mixing Coefficients of Geometrically Ergodic Markov Processes
Grunewalder, S. & Khaleghi, A., 1 Jan 2026, In: IEEE Transactions on Information Theory. 72, 2, p. 1305-1318 14 p.Research output: Contribution to journal › Article › peer-review
-
On Restless Linear Bandits
Khaleghi, A., 1 Jan 2025, In: IEEE Transactions on Information Theory. 71, 4, p. 2982-2990 9 p.Research output: Contribution to journal › Article › peer-review
-
Hasimoto frames and the Gibbs measure of the periodic nonlinear Schrödinger equation
Blower, G., Khaleghi, A. & Kuchemann-Scales, M., 1 Feb 2024, In: Journal of Mathematical Physics. 65, 2, 022705.Research output: Contribution to journal › Article › peer-review
Open Access -
Inferring the Mixing Properties of a Stationary Ergodic Process From a Single Sample-Path
Khaleghi, A. & Lugosi, G., 1 Jun 2023, In: IEEE Transactions on Information Theory. 69, 6, p. 4014-4026 13 p.Research output: Contribution to journal › Article › peer-review
-
Oblivious data for fairness with kernels
Grünewälder, S. & Khaleghi, A., 1 Jan 2021, In: Journal of Machine Learning Research. 22, p. 1-36 36 p.Research output: Contribution to journal › Article › peer-review
-
Clustering piecewise stationary processes
Khaleghi, A. & Ryabko, D., 1 Jun 2020, 2020 IEEE International Symposium on Information Theory, ISIT 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., p. 2753-2758 6 p. 9174045. (IEEE International Symposium on Information Theory - Proceedings; vol. 2020-June).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review
Open Access -
Approximations of the restless bandit problem
Grünewälder, S. & Khaleghi, A., 1 Feb 2019, In: Journal of Machine Learning Research. 20Research output: Contribution to journal › Article › peer-review
-
Consistent algorithms for clustering time series
Khaleghi, A., Ryabko, D., Mary, J. & Preux, P., 1 Jan 2016, In: Journal of Machine Learning Research. 17Research output: Contribution to journal › Article › peer-review
-
Nonparametric multiple change point estimation in highly dependent time series
Khaleghi, A. & Ryabko, D., 21 Mar 2016, In: Theoretical Computer Science. 620, p. 119-133 15 p.Research output: Contribution to journal › Article › peer-review
Open Access -
Asymptotically consistent estimation of the number of change points in highly dependent time series
Khaleghi, A. & Ryabko, D., 1 Jan 2014, 31st International Conference on Machine Learning, ICML 2014. International Machine Learning Society (IMLS), p. 824-832 9 p. (31st International Conference on Machine Learning, ICML 2014; vol. 1).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review