Research Overview

My research aims to devise efficient algorithms for addressing challenging problems, often they are NP-hard, within the realms of Applied Probability, Computational Statistics, Machine Learning, and Deep Learning. Keywords relevant to my research include Model Selection, Best Subset Selection, Monte Carlo Simulation, Spatial Point Processes, Bayesian Inference, Perfect Sampling, Importance Sampling, Unbiased Estimation, Large Deviations Theory, Variance Reduction Techniques, and Queueing Theory.

Explore the articles in the following topics for detailed insights into my research projects. Access my CV for a comprehensive list of publications.

Computational Statistics | Point Processes | Machine Learning | Deep Learning | Queueing Theory | Applied Projects

If you are a master's or honors student, or are eligible for a PhD and interested in collaborating on a project related to any of these topics, drop an email at

Computational Statistics

  • Mathur, A., Moka, S., Liquet, B., and Botev, Z. (2024) "Group COMBSS: Group Selection via Continuous Optimization”
    Submitted to Winter Simulation Conference [arXiv]

  • Nguyen, T., Moka, S., Mengersen, K., and Liquet, B. (2024) “Spatial Autoregressive Model on a Dirichlet Distribution”

  • Liquet, B., Moka, S., and Muller, S. (2024) “Best Subset Selection for Linear Dimension Reduction Models using Continuous Optimization”
    Submitted to Biometrical journal [arXiv]

  • Moka, S., Liquet, B., Zhu, H., and Muller, S. (2024) "COMBSS: Best Subset Selection via Continuous Optimization”
    Statistics and Computing [link] [arXiv]

  • Mathur, A., Moka, S., Botev, Z. (2024) “Column Subset Selection and Nyström Approximation via Continuous Optimization”
    Proceedings of Winter Simulation Conference [link] [arXiv]

  • Mathur, A., Moka, S., Botev, Z. (2023) “Feature Selection in Generalized Linear models via the Lasso: To Scale or Not to Scale?”
    OPT 2023: Optimization for Machine Learning [link] [arXiv]

  • Mathur, A., Moka, S., and Botev, Z. I. (2022) “Coordinate Descent for Variance Component Models”
    Algorithms [link]

  • Mathur, A., Moka, S. B., and Botev, Z. I. (2021) “Variance Reduction for Black Box Matrix Simulation with Applications to Gaussian Processes”
    ValueTools [link]

Point Processes

  • Moka, S. B., Juneja, S. and Mandjes, M. R. H. (2021) “Rejection and Importance Sampling based Perfect Simulation for Gibbs Hard-Spheres Processes”
    Advances in Applied Probability [link] [arXiv]

  • Hirsch, C., Moka, S. B., Taimre, T. and Kroese, D. (2021) “Rare Events in Random Geometric Graphs”
    Methodology and Computing in Applied Probability [link] [arXiv]

  • Moka, S. B. and Kroese, D.(2020) "Perfect Sampling for Gibbs Point Processes using Partial Rejection Sampling”
    Bernoulli [link] [arXiv]

  • Moka, S. B., Juneja, S. and Mandjes, M. R. H. (2018) "Analysis of Perfect Sampling Methods for Hard-sphere Models”
    SIGMETRICS Perform. Eval. Rev. [link]

  • Foss, S., Juneja, S., Mandjes, M. R. H. and Moka, S. B. (2015) "Spatial Loss Systems: Exact Simulation and Rare Event Behavior”
    SIGMETRICS Perform. Eval. Rev. [link]

Machine Learning

  • Moka, S. B., Juneja, S., and Kroese, D. (2019) “Unbiased Estimation of the Reciprocal Mean for Non-negative Random Variables”
    Proceedings of Winter Simulations Conference [link] [arXiv]

  • Jing Fu, Yoni Nazarathy, Sarat Moka, Peter Taylor. (2019) “Towards Q-learning the Whittle Index for Restless Bandits”
    Australian & New Zealand Control Conference [link] [pdf]

Deep Learning

  • [ONGOING] Mathur, A., Lee, S., Nguyen, T., Liquet, B., and Moka, S. (2024) “Pruning of Deep Neural Networks via Best Subject Selection”

  • [BOOK] Liquet, B., Moka, S., and Nazarathy, Y. (2024) “Mathematical Engineering of Deep Learning”
    CRC Press [pdf chapters]

  • [BOOK CHAPTER] Liquet, B., Moka, S., and Nazarathy, Y. (2024) “Navigating Mathematical Basics: A Primer for Deep Learning in Science”
    for the book Computational Neurosurgery in the book series Advances in Experimental Medicine and Biology. Editors: Antonio Di Ieva, Eric Suero Molina, Sidong Liu and Carlo Russo. [pdf]

Queueing Theory

  • Moka, S. B., Nazarathy, Y. and Scheinhardt, W. (2022) “Diffusion Parameters of Flows in Stable Multi-class Queueing Networks”
    Queueing Systems [link] [arXiv]

  • Moka, S. B. and Juneja, S. (2015) “Regenerative Simulation for Queueing Networks with Exponential or Heavier Tail Arrival Distributions”
    ACM Trans. Model. Comput. Simul. [link]

  • Moka, S. B. and Juneja, S. (2013) “Regenerative Simulation for Multiclass Open Queueing Networks”
    Proceedings of Winter Simulation Conference [link]

Applied Projects

  • Dandekar, R., Henderson, S. G., Jansen, M., McDonald, J., Moka, S. B., Nazarathy, Y., Rackauckas, C., Taylor, P. G., Vuorinen, A. (2021) “Safe Blues: A Method for Estimation and Control in the Fight Against COVID-19”
    Patterns Cell Press [link] [medRxiv] [website]

  • Shukla, A., Nguyen, T. H. M., Moka, S. B., Ellis, J. J., Grady, J. P., Oey, H., Cristino, A. S., Khanna, K. K., Kroese, D. P., Krause, L., Dray, E., Fink, J. L., Duijf, P. H. G. (2020) “Chromosome Arm Aneuploidies Shape Tumour Evolution, Cancer Prognosis and Drug Response”
    Nature Communications [link]