PeopleofSuperintelligence

Researcher

Leon Sallandt

Leon Sallandt is an applied mathematician whose research uses hierarchical tensors and tensor trains for high-dimensional optimal control and partial differential equations. He coauthored a stationary Bellman-equation method in November 2019, presented exit-time control work at a Max Planck Institute for Mathematics in the Sciences minisymposium in July 2020, and coauthored a policy-iteration paper on stochastic exit-time control in October 2020. In 2021, he coauthored studies on Bermudan option pricing and finite-horizon feedback controllers, and his ICML paper with Lorenz Richter and Nikolas Nüsken on parabolic PDEs received an Outstanding Paper Honorable Mention. Technische Universität Berlin accepted his doctoral thesis on high-dimensional value functions in December 2021 and issued it in 2022, and in 2024 he coauthored journal articles on stationary Bellman equations and robust regression for parabolic PDEs with a TU Berlin affiliation.

Timeline

  1. November 2019

    A stationary Bellman solver

    In November 2019, he coauthors a method for solving the stationary Hamilton-Jacobi-Bellman equation in high dimensions, using low-rank hierarchical tensor formats, including tensor trains, to approximate value functions.

  2. July 2020

    MPI MIS low-rank minisymposium talk

    In July 2020, while at Technische Universität Berlin, he presents a talk on solving stochastic exit-time control problems with tensor-train approximation at the Max Planck Institute for Mathematics in the Sciences online minisymposium on low-rank geometry and computation.

  3. October 2020

    Exit-time feedback control with tensor trains

    With Konstantin Fackeldey, Mathias Oster, and Reinhold Schneider in October 2020, he coauthors a paper on stochastic optimal exit-time feedback control driven by stochastic differential equations, solving the Bellman equation via policy iteration in the tensor-train format.

  4. March 2021

    Bermudan option pricing

    In March 2021, he and Christian Bayer, Martin Eigel, and Philipp Trunschke present a preprint on high-dimensional Bermudan option pricing with hierarchical tensors. It describes a tensor-train optimization procedure for high-dimensional polynomial expansions.

  5. April 2021

    Finite-horizon feedback control

    He coauthors a paper with Mathias Oster and Reinhold Schneider in April 2021 that applies low-rank hierarchical tensor formats to approximate optimal feedback controllers for finite-horizon control problems.

  6. July 2021

    ICML paper award for parabolic PDEs

    With Lorenz Richter and Nikolas Nüsken in July 2021, he publishes ICML work on tensor-train methods for high-dimensional parabolic PDEs, using backward stochastic differential equations and regression-based iterative schemes. The paper receives an Outstanding Paper Honorable Mention at ICML in 2021.

  7. December 2021–2022

    A doctoral thesis on control

    Technische Universität Berlin accepts his doctoral thesis on high-dimensional value functions for optimal feedback control in December 2021 and issues it in 2022. The thesis applies hierarchical tensor formats, including tensor trains, policy iteration, and Monte Carlo approximation.

  8. 2024

    Bellman and PDE journal papers

    In April 2024, the Journal of Computational Mathematics publishes his stationary Bellman-equation paper with Mathias Oster and Reinhold Schneider, listing him at Technische Universität Berlin. In 2024, he also coauthors a Journal of Machine Learning Research article with Lorenz Richter and Nikolas Nüsken on tensor trains, continuous-time iterative schemes, and robust regression for backward stochastic differential equations and parabolic PDEs.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Technische Universität Berlin. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Technische Universität Berlin. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Technische Universität Berlin. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. Google has the highest combined h-index among AI organizationsIncludes Technische Universität Berlin. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Leon Sallandt yet. Send us a free-licensed photo.

  1. Approximating the Stationary Bellman Equation by Hierarchical Tensor Products arxiv.org. Checked 22 October 2026.
  2. Online Minisymposium on Low-rank Geometry and Computation: MPI MIS mis.mpg.de. Checked 22 October 2026.
  3. Approximative Policy Iteration for Exit Time Feedback Control Problems driven by Stochastic Differential Equations using Tensor Train format arxiv.org. Checked 22 October 2026.
  4. Pricing high-dimensional Bermudan options with hierarchical tensor formats arxiv.org. Checked 22 October 2026.
  5. Approximating optimal feedback controllers of finite horizon control problems using hierarchical tensor formats arxiv.org. Checked 22 October 2026.
  6. Solving high-dimensional parabolic PDEs using the tensor train format proceedings.mlr.press. Checked 22 October 2026.
  7. ICML 2021 Awards icml.cc. Checked 22 October 2026.
  8. Computing high-dimensional value functions of optimal feedback control problems using the Tensor-train format depositonce.tu-berlin.de. Checked 22 October 2026.
  9. Approximating the Stationary Bellman Equation by Hierarchical Tensor Products global-sci.com. Checked 22 October 2026.
  10. From continuous-time formulations to discretization schemes: tensor trains and robust regression for BSDEs and parabolic PDEs jmlr.org. Checked 22 October 2026.