Nikolas Kantas

Reader in Statistics,
Dept. of Mathematics
Imperial College London

Email:
n . kantas AT imperial . ac . uk

Preprints

• Fast and robust consensus-based optimization via optimal feedback control,
  Y. Huang, M. Herty, D. Kalise, N. Kantas, November 2024.
  
• Random Pareto front surfaces,
  B. Tu, N. Kantas, R. Lee, B. Shafei, May 2024.
  
• Curvature Aligned Simplex Gradient: Principled Sample Set Construction For Numerical Differentiation,
  D. Lengyel, P. Parpas, N. Kantas, N. R. Jennings, October 2023.
  
• Privacy Risk for anisotropic Langevin dynamics using relative entropy bounds,
  A. Borovykh, N. Kantas, P. Parpas, G. A. Pavliotis, February 2023.
  

Journal papers

• Scalarisation-based risk concepts for robust multi-objective optimisation,
  B. Tu, N. Kantas, R. Lee, B. Shafei
  European Journal of Operational Research, to appear 2025.
  
• Multi-Objective Optimization Using the R2 Utility,
  B. Tu, N. Kantas, R. Lee, B. Shafei
  SIAM Review, to appear 2025.
• Stochastic Mirror Descent for Convex Optimization with Consensus Constraints,
  A. Borovykh, N. Kantas, P. Parpas, G. A. Pavliotis
  SIAM Journal on Applied Dynamical Systems, Vol. 23, Iss. 3, 2024.
• Sequential Markov Chain Monte Carlo for Lagrangian Data Assimilation with Applications to Unknown Data Locations,
  H. Ruzayqat, A. Beskos, D. Crisan, A. Jasra, N. Kantas,
  Quarterly Journal of the Royal Meteorological Society, 150(761), 2418–2439, 2024.
• Optimal friction matrix for underdamped Langevin sampling,
  M. Chak, N. Kantas, T. Lelièvre, G. A. Pavliotis,
  ESAIM: Mathematical Modelling and Numerical Analysis, 57 (6), 3335-3371, 2023.
• Online parameter Estimation for the McKean-Vlasov Stochastic Differential Equation,
  L. Sharrock, N. Kantas, P. Parpas, G. A. Pavliotis,
  Stochastic Processes and their Applications, Vol 162, Pages 481-546, 2023.
  Code used for paper available here.
  
• Unbiased Estimation using a Class of Diffusion Processes,
  H. Ruzayqat, A. Beskos, D. Crisan, A. Jasra, N. Kantas,
  Journal of Computational Physics, Volume 472, 111643, 2023. [arXiv]
• On the Generalised Langevin Equation for Simulated Annealing,
  M. Chak, N. Kantas, G. A. Pavliotis,
  SIAM/ASA Journal of Uncertainty Quantification, Vol. 11, Iss. 1, 2023. [arXiv]
• Two- Timescale Stochastic Gradient Descent in Continuous Time with Applications to Joint Online Parameter Estimation and Optimal Sensor Placement,
  L. Sharrock, N. Kantas,
  Bernoulli, 29(2): 1137-1165, 2023. [arXiv]
• A Lagged Particle Filter for Stable Filtering of certain High-Dimensional State-Space Models,
  H. Ruzayqat, A. Er-Raiy, A. Beskos, D. Crisan, A. Jasra, N. Kantas,
  SIAM/ASA Journal of Uncertainty Quantification, Vol. 10, Iss. 3, 2022. [arXiv]
• Joint Online Parameter Estimation and Optimal Sensor Placement for the Partially Observed Stochastic Advection-Diffusion Equation,
  L. Sharrock and N. Kantas
  SIAM/ASA Journal of Uncertainty Quantification, 10(1), 55–95, 2022. [arXiv]
  Code used for paper available here.
• Score-Based Parameter Estimation for a Class of Continuous-Time State Space Models,
  A. Beskos, D. Crisan, A. Jasra, N. Kantas, H. Ruzayqat,
  SIAM Journal of Scientific Computing, 43(4), A2555–A2580, 2021. [arXiv]
  Code used for paper available here
• Key epidemiological drivers and impact of interventions in the 2020 SARS-CoV-2 epidemic in England,
  E. S. Knock, L. K. Whittles, J. A. Lees, P. N. Perez-Guzman, R. Verity, R. G. FitzJohn, K. A. M. Gaythorpe, N.Imai, W. Hinsley, L. C. Okell, A. Rosello, N. Kantas, C. E. Walters, S. Bhatia, O. J. Watson, C. Whittaker, L. Cattarino, A. Boonyasiri, B. A. Djaafara, K. Fraser, H. Fu, H. Wang, X. Xi, C. A. Donnelly, E. Jauneikaite, D. J. Laydon, P. J. White, A. C. Ghani, N. M. Ferguson, A. Cori, M. Baguelin,
  Science Translational Medicine, June 2021.
• On Stochastic Mirror Descent with Interacting Particles: Convergence Properties and Variance Reduction,
  A. Borovykh, N. Kantas, P. Parpas, G. A. Pavliotis,
  Physica D: Nonlinear Phenomena, Vol 418, April 2021, 132844.
• Factor Augmented Bayesian Cointegration Model: a case study on the Soybean Crush Spread,
  M. Marowka, G. W. Peters, N. Kantas and G. Bagnarosa,
  Journal of the Royal Statistical Society Series C, Vol. 69, Issue 2, pp. 483-500, 2020. Supplementary Material.
  Code and data here
• On Adaptive Estimation for Dynamic Bernoulli Bandits,
  X. Lu, N. Adams, and N. Kantas,
  Foundations of Data Science, Vol 1, No. 2, pp. 197-225, 2019.
• Particle Filtering for Stochastic Navier-Stokes Signals Observed with Linear Additive Noise,
  F. Pons Llopis, N. Kantas, A. Beskos and A. Jasra,
  SIAM Journal of Scientific Computing, Vol. 40, No. 3, pp. A1544–A1565, 2018. [arXiv]
  Code used for paper available here
• Some Recent Developments in Markov Chain Monte Carlo for Cointegrated Time Series,
  M. Marowka, G. W. Peters, N. Kantas and G. Bagnarosa,
  ESAIM Proceedings and Surveys, Vol. 59, p. 76-103, 2017
• Calculating principal eigen-functions of non-negative integral kernels: particle approximations and applications,
  N. Whiteley and N. Kantas,
  Mathematics of Operations Research, Vol. 42, No. 4, 1007-1034, 2017. [arXiv]
• On the Convergence of Adaptive Sequential Monte Carlo Methods,
  A. Beskos, A. Jasra, N. Kantas and A. Thiery,
  Annals of Applied Probability, 26, 2, pp 1111-1146, 2016.
• On Particle Methods for Parameter Estimation in General State-Space Models,
  N. Kantas, A. Doucet, S. S. Singh, J. M. Maciejowski and N. Chopin,
  Statistical Science, Vol. 30, No. 3, 328-351, 2015.
  Code used for paper available here
• Gradient Free Parameter Estimation for Hidden Markov Models with Intractable Likelihoods,
  E. Ehrlich, A. Jasra and N. Kantas,
  Methodology and Computing in Applied Probability, Volume 17, Issue 2, pp 315–349, 2015.
• Sequential Monte Carlo Methods for High-Dimensional Inverse Problems: A case study for the Navier-Stokes equations,
  N. Kantas, A. Beskos and A. Jasra,
  SIAM/ASA Journal of Uncertainty Quantification, 2, 464-489, 2014. [arXiv]
  Code used for paper available here
• Approximate inference for observation driven time series models,
  A. Jasra, N. Kantas and E. Ehrlich,
  ACM Transactions of Modeling and Computer Simulation (TOMACS), Vol. 24, No. 3, Article 13, 2014. [arXiv]
• Bayesian Parameter Inference for Partially Observed Stopped Processes,
  A. Jasra, N. Kantas and A. Persing,
  Statistics and Computing, vol 24, Issue 1, pp 1-20, 2014. [arXiv]
• Linear Variance Bounds for Particle Approximations of Time-Homogeneous Feynman-Kac Formulae,
  N. Whiteley, N. Kantas, A. Jasra,
  Stochastic Processes and their Applications, vol 122, Issue 4, pp. 1840-1865, 2012. [arXiv]
• Distributed Maximum Likelihood with application to simultaneous self-localization and tracking for sensor networks,
  N. Kantas, S. S. Singh, A. Doucet,
  IEEE Transactions of Signal Processing, vol 60, Issue 10, pp. 5038 - 5047, 2012. [arXiv],
  Code used for paper available here
• Simulation Based Bayesian Optimal Design of Aircraft Trajectories for Air Traffic Management,
  N. Kantas, A. Lecchini-Visintini, J. M. Maciejowski,
  International Journal of Adaptive Control and Signal Processing, vol 24, Issue 10, pp. 882-899, 2010.
• Simulation-Based Optimal Sensor Scheduling with Application to Observer Trajectory Planning,
  S.S. Singh, N. Kantas, B. Vo, A. Doucet and R. Evans,
  Automatica, vol. 43, no. 5, pp. 817-830, 2007.

Conference papers

• Joint Entropy Search for Multi-Objective Bayesian Optimization,
  B. Tu, A. Gandy, N. Kantas, B. Shafei,
  In Proc. Advances in Neural Information Processing Systems 35 (NeurIPS), 2022
• Optimizing interacting Langevin dynamics using spectral gaps,
  A. Borovykh, N. Kantas, P. Parpas, G.A. Pavliotis,
  In Proc. of Workshop on Beyond First Order Methods in Machine Learning at International Conference on Machine Learning (ICML), 2021.
• Stochastic mirror descent for fast distributed optimization and federated learning,
  A. Borovykh, N. Kantas, P. Parpas, G.A. Pavliotis,
  In Proc. OPT2020: 12th Annual Workshop on Optimization for Machine Learning, 2020.
• To interact or not? The convergence properties of interacting stochastic mirror descent,
  A. Borovykh, N. Kantas, P. Parpas, G.A. Pavliotis,
  In Proc. of Workshop on "Beyond first-order methods in ML systems" at 36th International Conference on Machine Learning (ICML) 2020.
• The sharp, the flat and the shallow: Can weakly interacting agents learn to escape bad minima?,
  N. Kantas, P. Parpas, G.A. Pavliotis,
  In Proc. of ICML 2019 Workshop on AI in Finance: Applications and Infrastructure for Multi-Agent Learning, June 14th 2019, Long Beach, CA, USA.
• Stable Markov decision processes using simulation based predictive control,
  Z. Yang, N. Kantas, A. Lecchini-Visintini, J.M. Maciejowski,
  In Proc. 19th International Symposium on Mathematical Theory of Networks and Systems, MTNS 2010, 5-9 July 2010, Budapest, Hungary.
• Overview of Sequential Monte Carlo methods for parameter estimation on general state space models,
  N. Kantas, A. Doucet, S.S. Singh, J. M. Maciejowski,
  In Proc. 15th IFAC Symposium on System Identification (SYSID) 2009, Saint-Malo, France.
• Stability of Model Predictive Control using Markov Chain Monte Carlo Optimisation,
  E. Siva, P. Goulart, J.M. Maciejowski, N. Kantas,
  In Proc. 10th European Control Conference (ECC) 2009, Budapest, Hungary.
• Sequential Monte Carlo for Model Predictive Control,
  N. Kantas, J. M. Maciejowski, A. Lecchini-Visintini,
  In Nonlinear Model Predictive Control Towards New Challenging Applications Series: Lecture Notes in Control and Information Sciences, Vol. 384, Magni, Lalo; Raimondo, Davide Martino; Allgoewer, Frank (Eds.), 2009.
• Distributed Online Self-Localization and Tracking in Sensor Networks,
  N. Kantas, S. S. Singh, A. Doucet,
  In Proc of the International Symposium on Image and Signal Processing and Analysis (ISPA) 2007, Istanbul, Turkey.
• Distributed Self Localisation of Sensor Networks using Particle Methods,
  N. Kantas, S. S. Singh, A. Doucet,
  In Proc. of the Nonlinear Statistical Signal Processing Workshop (NSSPW) 2006, Cambridge, UK.
• A Distributed Recursive Maximum Likelihood Implementation for Sensor Registration,
  N. Kantas, S. S. Singh, A. Doucet,
  In Proc. of the 9th International Conference on Information Fusion (Fusion) 2006, Florence, Italy.
• Simulation-Based Optimal Sensor Scheduling with Application to Observer Trajectory Planning,
  S. S. Singh, N. Kantas, B. Vo, A. Doucet and R. Evans,
  In Proc.of the 44th IEEE Conference on Decision and Control and European Control Conference (CDC-ECC) 2005, Sevilla, Spain.

Other

• Discussion of "Unbiased MCMC methods with couplings" by Jacob, O' Leary and Atchade,
  M. Chak, N. Kantas, G. A. Pavliotis,
  Journal of the Royal Statistical Society Series B, 2020.
• Estimation of Cointegrated Spaces: A Numerical Case Study on Efficiency, Accuracy and Influence of the Model Noise,
  M. Marowka, G. W. Peters, N. Kantas and G. Bagnarosa,
  Technical Report, a significantly revised version appeared as the paper in ESAIM Proceedings and Surveys above.
• On the convergence of a stochastic optimisation algorithm for optimal observer trajectory planning,
  S. S. Singh, N. Kantas, B. Vo, A. Doucet and R. Evans
  Technical Report CUED/F-INFENG/TR 522, University of Cambridge, Department of Engineering, March 2005.
• Sequential Decision Making for General State Space Models, PhD Thesis, Department of Engineering, University of Cambridge, Feb. 2009.