Machine learning for quantum systems

Statistical estimation applied to quantum states and devices.

Classical machine-learning algorithms are well suited to many quantum applications. I have used classical ML techniques to study quantum ground states of lattice models, develop quantum tomography algorithms, and characterize near-term quantum devices, among other applications. Much of my postdoctoral work has focused on problems along these lines.

Papers

  1. Efficient learning of lattice gauge theories with fermions
    Shreya Shukla, Yukari Yamauchi, Andrey Y. Lokhov , and 2 more authors
    Phys. Rev. D, Jun 2026
  2. Operator Score Matching for Learning Quantum Hamiltonians
    Shreya Shukla, Abhijith Jayakumar, and Andrey Y Lokhov
    arXiv preprint arXiv:2609.25246, 2026
  3. Learning response functions of analog quantum computers: analysis of neutral-atom and superconducting platforms
    Cenk Tüysüz, Abhijith Jayakumar, Carleton Coffrin , and 2 more authors
    arXiv preprint arXiv:2503.12520, 2025
  4. Autoregressive Pairwise Graphical Models Efficiently Find Ground State Representations of Stoquastic Hamiltonians
    Yuchen Pang, Abhijith Jayakumar, Evan McKinney , and 3 more authors
    In 2025 IEEE International Conference on Quantum Computing and Engineering (QCE) , 2025
  5. Learning energy-based representations of quantum many-body states
    Abhijith Jayakumar, Marc Vuffray, and Andrey Y. Lokhov
    Phys. Rev. Res., Aug 2024
  6. Universal framework for simultaneous tomography of quantum states and SPAM noise
    Abhijith Jayakumar, Stefano Chessa, Carleton Coffrin , and 3 more authors
    Quantum, Jul 2024
All research Full publication list