JERAJournal of Electronic Research and Application2208-35022208-3510Bio-Byword Scientific Publishing Pty. Ltd.10.26689/jera.v10i7.15841ArticlePolynomial Mitigation of the Fermionic Sign Problem via Topological Neural Flows and Generalized Complex Manifold Deformationshttps://artdesignp.com/journal/JERA/10/7/10.26689/jera.v10i7.15841LiuKaiyang20261072026-08-11Since the discovery of the sign problem in the 1980s, all unbiased numerical methods have failed to avoid the exponential growth of computational complexity when simulating strongly correlated fermions at finite densities. This paper proves that by analytically continuing the path integral to a continuous complex manifold and transforming it into an unsupervised geometric optimization problem, this exponential wall can be systematically mitigated. We introduce the Topological Neural Flow (TNF) framework, utilizing Equivariant Continuous Normalizing Flows constrained by Cauchy’s integral theorem to dynamically learn a deformation contour that minimizes the imaginary phase variance of the effective action. Focusing on the highly challenging 2D hole-doped repulsive Hubbard model, we demonstrate exponential sign mitigation on lattices up to 10 × 10, reducing the required number of Monte-Carlo samples by up to 8 orders of magnitude. We explicitly map the critical breakdown point of the method at the 12 × 12 scale, establishing a rigorous mathematical and physical foundation for AI-assisted path integral contour deformations.

Rodekamp M, Berkowitz E, Gäntgen C, et al., 2022, Mitigating the Hubbard Sign Problem with Complex-Valued Neural Networks. Physical Review B, 106(12): 125139.

Carleo G, Troyer M, 2017, Solving the Quantum Many-Body Problem with Artificial Neural Networks. Science, 355(6325): 602–606.

Wynen J, Berkowitz E, Krieg S, et al., 2021, Machine Learning to Alleviate Hubbard-Model Sign Problems. Physical Review B, 103(12): 125153.

Kanwar G, Albergo M, Boyda D, et al., 2020, Equivariant Flow-Based Sampling for Lattice Gauge Theory. Physical Review Letters, 125(12): 121601.

Albergo M, Kanwar G, Shanahan P, 2019, Flow-Based Generative Models for Markov Chain Monte Carlo in Lattice Field Theory. Physical Review D, 100(3): 034515.

Troyer M, Wiese U, 2005, Computational Complexity and Fundamental Limitations to Fermionic QMC. Physical Review Letters, 94(17): 170201.

Alexandru A, Bedaque P, Lamm H, et al., 2018, Finite-Density Monte Carlo Calculations on Sign-Optimized Manifolds. Physical Review D, 97(9): 094510.

Alexandru A, Basar G, Bedaque P, et al., 2016, Sign Problem and Monte Carlo Calculations Beyond Lefschetz Thimbles. Journal of High Energy Physics, 2016(5): 1–17.

Gerdes M, de Haan P, Bondesan R, et al., 2024, Continuous Normalizing Flows for Lattice Gauge Theories. arXiv e-prints, arXiv:2410.

Pfau D, Spencer J, Matthews A, et al., 2020, Ab Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks. Physical Review Research, 2(3): 033429.