Two complementary gradient computation methods are developed for differentiable parameter optimization of semi-explicit DAEs with state-dependent events.
Ascher and Linda R
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
The paper introduces penalty-based and randomized-exploration adaptations to flow matching for improved constraint satisfaction in generative models while matching target distributions.
citing papers explorer
-
Differentiable Parameter Optimization for DAEs with State-Dependent Events
Two complementary gradient computation methods are developed for differentiable parameter optimization of semi-explicit DAEs with state-dependent events.
-
Constraint-Aware Flow Matching via Randomized Exploration
The paper introduces penalty-based and randomized-exploration adaptations to flow matching for improved constraint satisfaction in generative models while matching target distributions.