Fractional Physics Informed Neural Networks for Surrogate Modeling of Non-Markovian Discrete-Time Quantum Walks
Zhaoyu Zhu, Mingxin Liu, Chengtian Liang, Fan Yang, Jizhong Shen, Xintong Wen, Lijiong Shen, Yu Wang · 2026
Read Fractional Physics Informed Neural Networks for Surrogate Modeling of Non-Markovian Discrete-Time Quantum Walks by Zhaoyu Zhu, Mingxin Liu, Chengtian Liang, Fan Yang, Jizhong Shen, Xintong Wen, Lijiong Shen, Yu Wang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13511913.txt.
Description
Zhaoyu Zhu and colleagues built FracPINN, a neural network with built-in physics rules, to predict how quantum walks spread under memory-carrying noise. Quantum walks model particles whose paths interfere, and noisy surroundings can slow or speed their spread in odd ways.
The model blends a sequence-learning network with a solver for fractional spread equations, the maths of memory-driven transport. On 3,709 held-out simulations, it beat plain data-driven rivals, cutting average error by 5.3 percent overall. Gains were largest, 13.5 percent, in the slow-spreading regime where memory effects dominate, while other regimes stayed accurate. Once trained, it answers in a fraction of a millisecond instead of seconds of simulation, Zhu reports.
Catalog record
| CREATOR | Zhaoyu Zhu, Mingxin Liu, Chengtian Liang, Fan Yang, Jizhong Shen, Xintong Wen, Lijiong Shen, Yu Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |