Vyacheslav Kungurtsev

Vyacheslav Kungurtsev

I'm an Applied Mathematician with expertise in Optimization, Process Control Engineering, Distributed decentralized and high performance computing, ML and AI . Currently based in Prague.

Publications

Publications

My work spans numerical optimization, control, distributed and federated learning, scientific machine learning, quantum optimization, and applications. The publication record below is organized around recent research themes, with a separate complete Google Scholar snapshot for exhaustive browsing.

1,790Google Scholar citations
23h-index
43i10-index

Google Scholar snapshot supplied 9 August 2026; citation metrics change over time.

Full publication list → Live Google Scholar →

Recent work — running summary

2026. The current year extends the OORDSU theme in several directions: real-time control of nonlinear hyperbolic PDE models for water engineering; learning the global/local trade-off in optimization; iterative linear algebra across heterogeneous parallel backends; rare-event stochastic programming for power systems; and three-tier control architectures. Parallel work develops symplectic neural networks for generalized Hamiltonians, decentralized derivative-free optimization, stochastic acceleration, sparse optimization, quantum algorithms, dataset distillation, and data-driven biomedical applications.

2025. Work ranges from stochastic interior-point methods and parametric semidefinite programming to dataset distillation, federated learning, autonomous-system control, scientific ML, solver-assisting machine learning, robust/Byzantine federated learning, and optimization under scientific structure. This period substantially expands the connection between optimization theory and deployment-oriented AI.

2024. Publications include variational quantum algorithm complexity, Riemannian derivative-free optimization, functional constrained stochastic optimization, bilevel methods, time-varying SDP, federated learning, and dataset distillation at CVPR, ECCV, NeurIPS, and ICLR-associated work.

Selected 2026 publications and preprints

  1. M. Kimiaei, S. Babaie–Kafaki, V. Kungurtsev, M. Yousefi. Restarting two-term nonlinear conjugate gradient methods based on a finite precision arithmetic analysis. Journal of Computational and Applied Mathematics 488, 117856, 2026.
  2. H. Choudhary, V. Kungurtsev, C. Gupta, M. Leok, G. Korpas. Symplectic Neural Networks for learning Generalized Hamiltonians. arXiv:2606.27029, 2026.
  3. F. DiFonzo, M. Holst, M. Kimiaei, V. Kungurtsev, S. Qiu. Towards real time control of water engineering with nonlinear hyperbolic partial differential equations. Journal of Computational Science, 102945, 2026.
  4. Y. Cao, J. Gu, V. Kungurtsev, Y. Hu, J. Hamari, Z. Liu, M. Zardadi. Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space. arXiv:2606.21705, 2026.
  5. H. Attouch, J. Fadili, V. Kungurtsev. The stochastic Ravine accelerated gradient method with general extrapolation coefficients. Journal of Optimization Theory and Applications 209(1), 5, 2026.
  6. E. Bergou, Y. Diouane, V. Kungurtsev, C. W. Royer. Direct-search methods for decentralized blackbox optimization. Optimization Methods and Software, 1–22, 2026.
  7. D. Waldner, V. Kungurtsev, M. Ashimosi. Noncooperative Human-AI Agent Dynamics. arXiv:2603.16916, 2026.
  8. D. Mastropietro, V. Kungurtsev. Multistage Stochastic Programming for Rare Event Risk Mitigation in Power Systems Management. arXiv:2603.04734, 2026.
  9. V. Kungurtsev, G. Russo. Towards Tsallis Fully Probabilistic Design. arXiv:2602.23892, 2026.
  10. V. Kungurtsev. A Three-Tier Time-Scale Architecture for Controlling Complex Nonlinear Systems. arXiv:2601.01621, 2026.

Selected recent publications

  • F. E. Curtis, V. Kungurtsev, D. P. Robinson, Q. Wang. A stochastic-gradient-based interior-point algorithm for solving smooth bound-constrained optimization problems. SIAM Journal on Optimization 35(2), 1030–1059, 2025.
  • S. Ma, J. Mareček, V. Kungurtsev, M. Tyburec. Truss topology design under harmonic loads: peak power minimization with semidefinite programming. Structural and Multidisciplinary Optimization 68(2), 40, 2025.
  • A. Bellon, D. Henrion, V. Kungurtsev, J. Mareček. Parametric semidefinite programming: geometry of the trajectory of solutions. Mathematics of Operations Research 50(1), 410–430, 2025.
  • S. Vahidian, M. Wang, J. Gu, V. Kungurtsev, W. Jiang, Y. Chen. Group distributionally robust dataset distillation with risk minimization. ICLR, 2025.
  • V. Kungurtsev, F. Rinaldi, D. Zeffiro. Retraction-based direct search methods for derivative free Riemannian optimization. Journal of Optimization Theory and Applications 203(2), 1710–1735, 2024.
  • V. Kungurtsev, G. Korpas, J. Marecek, E. Y. Zhu. Iteration complexity of variational quantum algorithms. Quantum 8, 1495, 2024.
  • M. Morafah, V. Kungurtsev, H. Chang, C. Chen, B. Lin. Towards diverse device heterogeneous federated learning via task arithmetic knowledge integration. NeurIPS, 2024.
  • J. Gu, S. Vahidian, V. Kungurtsev, H. Wang, W. Jiang, Y. You, Y. Chen. Efficient dataset distillation via minimax diffusion. CVPR, 2024.
  • Y. Jia et al. Unlocking the potential of federated learning: The symphony of dataset distillation via deep generative latents. ECCV, 2024.
  • A. Bellon, M. Dressler, V. Kungurtsev, J. Marecek, A. Uschmajew. Time-varying semidefinite programming: Path following a Burer–Monteiro factorization. SIAM Journal on Optimization 34(1), 1–26, 2024.

Earlier highlights

  • L. Cannelli, F. Facchinei, V. Kungurtsev, G. Scutari. Asynchronous parallel algorithms for nonconvex optimization. Mathematical Programming 184, 121–154, 2020.
  • E. H. Bergou, Y. Diouane, V. Kungurtsev. Convergence and complexity analysis of a Levenberg–Marquardt algorithm for inverse problems. Journal of Optimization Theory and Applications 185(3), 927–944, 2020.
  • A. Daneshmand, G. Scutari, V. Kungurtsev. Second-order guarantees of distributed gradient algorithms. SIAM Journal on Optimization 30(4), 3029–3068, 2020.
  • P. E. Gill, V. Kungurtsev, D. P. Robinson. A shifted primal-dual penalty-barrier method for nonlinear optimization. SIAM Journal on Optimization 30(2), 1067–1093, 2020.
  • P. E. Gill, V. Kungurtsev, D. P. Robinson. A stabilized SQP method: superlinear convergence. Mathematical Programming 163, 369–410, 2017.
  • A. Daneshmand, F. Facchinei, V. Kungurtsev, G. Scutari. Hybrid random/deterministic parallel algorithms for convex and nonconvex big data optimization. IEEE Transactions on Signal Processing 63(15), 3914–3929, 2015.

Complete record

The full publication page reproduces the complete Google Scholar list supplied in August 2026. The archived March 2026 CV remains available for the broader professional record.

Full publication list → · CV (March 2026) → · Google Scholar →