{"ID":2897215,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.06342","arxiv_id":"2507.06342","title":"SymFlux: deep symbolic regression of Hamiltonian vector fields","abstract":"We present SymFlux, a novel deep learning framework that performs symbolic regression to identify Hamiltonian functions from their corresponding vector fields on the standard symplectic plane. SymFlux models utilize hybrid CNN-LSTM architectures to learn and output the symbolic mathematical expression of the underlying Hamiltonian. Training and validation are conducted on newly developed datasets of Hamiltonian vector fields, a key contribution of this work. Our results demonstrate the model's effectiveness in accurately recovering these symbolic expressions, advancing automated discovery in Hamiltonian mechanics.","short_abstract":"We present SymFlux, a novel deep learning framework that performs symbolic regression to identify Hamiltonian functions from their corresponding vector fields on the standard symplectic plane. SymFlux models utilize hybrid CNN-LSTM architectures to learn and output the symbolic mathematical expression of the underlying...","url_abs":"https://arxiv.org/abs/2507.06342","url_pdf":"https://arxiv.org/pdf/2507.06342v1","authors":"[\"M. A. Evangelista-Alvarado\",\"P. Suárez-Serrato\"]","published":"2025-07-08T19:07:16Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"math.DS\",\"math.SG\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false}