ML: Dynamics

Machine-learning ideas tagged Dynamics in the ML taxonomy of the Math2NN corpus.

2 ideas found

Solves: Scalability ML: Dynamics Clear all

✗ Mechanism failed 2026

Nonlinear Laplacian Equilibrium GNN Layer

Replace several fixed message-passing layers with an implicit graph layer whose state is the solution of a nonlinear flow equilibrium. Learn monotone edge laws from endpoint features, solve for node potentials with damped chord-Newton steps, and use the resulting edge flows or potentials as the layer output. Monotonicity and the Laplacian Jacobian provide a principled stability mechanism while retaining sparse graph computation.

Useful7/10

Difficulty6/10

Novelty7/10

Architecture Accuracy Stability Scalability

Paper: NLF: A Resistor-Network Framework and Linear-Time Solver for Convex Network-Flow Equilibria arXiv:2607.02041

Unverified 2026

Hard Sequential Neural ODE Solver

Partition a long integration interval into M short segments and assign one neural trajectory approximator to each segment. Instead of asking a single network to satisfy the ODE and initial condition over the entire horizon, construct every segment so that its value at the left boundary is exactly the terminal value predicted by the previous segment. This removes interface discontinuities from the optimization problem and should improve long-horizon trajectory accuracy and gradient stability.

Useful6/10

Difficulty5/10

Novelty6/10

Dynamics Stability Accuracy Scalability

Paper: Modeling of an ODE-constrained optimization problem describing tumor dynamics, and numerical approximation via sequential physics-informed neural networks arXiv:2608.18974