Signature kernel and Schwinger-Dyson kernel equations are recast as two-parameter rough differential equations with well-posedness, stability, and a numerical scheme established for rough driving signals.
arXiv preprint arXiv:2404.02926 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Introduces the first explicit near-reversible integrator for neural SDEs on Lie groups by extending EES schemes with Bazavov's commutator-free lift, achieving better stability and up to 10x memory reduction on manifold benchmarks.
citing papers explorer
-
Signature Kernel and Schwinger-Dyson Kernel Equations as Two-Parameter Rough Differential Equations
Signature kernel and Schwinger-Dyson kernel equations are recast as two-parameter rough differential equations with well-posedness, stability, and a numerical scheme established for rough driving signals.
-
Explicit and Effectively Symmetric Schemes for Neural SDEs on Lie Groups
Introduces the first explicit near-reversible integrator for neural SDEs on Lie groups by extending EES schemes with Bazavov's commutator-free lift, achieving better stability and up to 10x memory reduction on manifold benchmarks.