The framework trains chaotic surrogates by minimizing MMD between pushforward distributions of local phase-space coverings under the model and ground truth, yielding improved Jacobian accuracy while staying competitive on statistical fidelity.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Watch your neighbors: Training statistically accurate chaotic systems with local phase space information
The framework trains chaotic surrogates by minimizing MMD between pushforward distributions of local phase-space coverings under the model and ground truth, yielding improved Jacobian accuracy while staying competitive on statistical fidelity.