ML: Dynamics

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

2 ideas found

△ Mechanism confirmed, baseline not beaten 2026

Unconditionally Positive Gain-Loss Neural ODE

Replace an unconstrained Neural ODE vector field with nonnegative production and destruction networks and discretize the resulting dynamics by an NSFD rational update. The update remains nonnegative for every step size, allowing stable coarse-step training and inference without clipping, projection, or tiny adaptive solver steps.

Useful8/10

Difficulty4/10

Novelty7/10

Dynamics Stability Accuracy Speedup

Paper: Structure-Preserving Neural ODEs via Nonstandard Finite Difference Discretization arXiv:2607.10858

✗ Mechanism failed 2026

Chebyshev-Stabilized SDIRK Neural ODE

Replace explicit RK integration in a stiff neural ODE or continuous-depth residual network with the paper's stiffly accurate SDIRK4 discretization. Instead of performing a dense Newton solve for each implicit stage, solve the diagonal stage equation using a Chebyshev-accelerated residual iteration whose polynomial damps the negative, high-magnitude Jacobian modes responsible for stiffness.

Useful6/10

Difficulty7/10

Novelty7/10

Dynamics Stability Speedup Accuracy

Paper: Explicit stabilized implementation of singly diagonally implicit Runge-Kutta methods arXiv:2607.07497