A maximum-likelihood-trained Neural SDE with diagonal diffusion is proposed as a unified, simulation-free method for continuous-domain sequence modeling, tested on branching trajectories, Push-T imitation, and KTH/CLEVRER video prediction.
Numerical solutions of stochastic differen- tial equations (kloeden, pk and platen, e.; 2008)[book reviews]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Neural SDEs as a Unified Approach to Continuous-Domain Sequence Modeling
A maximum-likelihood-trained Neural SDE with diagonal diffusion is proposed as a unified, simulation-free method for continuous-domain sequence modeling, tested on branching trajectories, Push-T imitation, and KTH/CLEVRER video prediction.