Dr Iñaki Esnaola
School of Electrical and Electronic Engineering
Senior Lecturer
+44 114 222 5648
Full contact details
School of Electrical and Electronic Engineering
Amy Johnson Building
Portobello Street
Sheffield
S1 3JD
- Profile
-
I received my MSc in Electrical Engineering from the University of Navarra, Spain in 2006 and a PhD in Electrical Engineering from the University of Delaware, Newark, DE in 2011. I am currently a Senior Lecturer in the Department of Automatic Control and Systems Engineering at The University of Sheffield, and a Visiting Research Collaborator in the Department of Electrical Engineering at Princeton University, NJ.
In 2010-2011 I was a Research Intern at Bell Laboratories, Alcatel-Lucent, Holmdel, NJ, and in 2011-2013 I was a Postdoctoral Research Associate at Princeton University. My research interests include information theory and communication theory with an emphasis on the application to electricity grid problems.
- Research interests
-
I am interested in understanding the role of information in monitoring, communication, and decision making systems. My research lies broadly in:
- Information theory and data science
- Machine learning and high-dimensional statistics
- Cybersecurity
- Detection and mitigation of data integrity attacks
- Privacy and confidentiality
- Information processes on cyberphysical systems
- Robust estimation with imperfect information
- Optimal sensor placement problems
- Publications
-
Journal articles
- TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models.. CoRR, abs/2507.10643.
- Asymmetry of the Relative Entropy in the Regularization of Empirical Risk Minimization. IEEE Transactions on Information Theory, 71(8), 6198-6226.
- Information-theoretic sensor placement for large sewer networks. Water Research, 268(Pt B). View this article in WRRO
- An information theoretic metric for measurement vulnerability to data integrity attacks on smart grids. IET Smart Grid, 7(5), 583-592. View this article in WRRO
- The worst-case data-generating probability measure in statistical learning. IEEE Journal on Selected Areas in Information Theory, 5, 175-189. View this article in WRRO
- Empirical risk minimization with relative entropy regularization. IEEE Transactions on Information Theory, 70(7), 5122-5161. View this article in WRRO
Conference proceedings
- A Dual Optimization View to Empirical Risk Minimization with f-Divergence Regularization. 2025 IEEE Information Theory Workshop (ITW) (pp 740-745), 29 September 2025 - 3 October 2025.
- Compressive Sensing with Augmented Measurements via Generative Self-Distillation. 2025 IEEE Statistical Signal Processing Workshop (SSP) (pp 31-35), 8 June 2025 - 11 June 2025.
- Equivalence of Empirical Risk Minimization to Regularization on the Family of $f- text{Divergences}$. 2024 IEEE International Symposium on Information Theory (ISIT) (pp 759-764), 7 July 2024 - 12 July 2024.
- Stability of Nonlinear Model Predictive Control Under Consecutive Packet Losses. 2024 UKACC 14th International Conference on Control (CONTROL) (pp 295-300), 10 April 2024 - 12 April 2024.
- Generalization analysis of machine learning algorithms via the worst-case data-generating probability measure. Proceedings of the 38th AAAI Conference on Artificial Intelligence, Vol. 38(15) (pp 17271-17279). Vancouver, Canada, 20 February 2024 - 20 February 2024. View this article in WRRO
- Stability and the separation principle in output-feedback stochastic MPC with random packet losses. IFAC-PapersOnLine, Vol. 56(2) (pp 3818-3823). Yokohama, Japan, 9 July 2023 - 9 July 2023. View this article in WRRO
- On the Validation of Gibbs Algorithms: Training Datasets, Test Datasets and their Aggregation. 2023 IEEE International Symposium on Information Theory (ISIT) (pp 328-333), 25 June 2023 - 30 June 2023.
- Analysis of the Relative Entropy Asymmetry in the Regularization of Empirical Risk Minimization. 2023 IEEE International Symposium on Information Theory (ISIT) (pp 340-345), 25 June 2023 - 30 June 2023.
Preprints
- TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models.. CoRR, abs/2507.10643.
- Grants
-
Research Grants
- Sustainable advanced manufacturing via machine learning-assisted exploitation of sensing and data infrastructure, RCUK, 01/09/2022 - 31/03/2023, £58,153, as PI
- Teaching activities
-
- ACS232 Signals, Systems, and Communications
- ACS6106 Cybersecurity for control systems
- Professional activities and memberships
-
Patents
Tulino AM & Esnaola I (2013) Method Apparatus for Low Complexity Robust Reconstruction of Noisy Signals. (United States). Appl. 21 Mar 2013