2 papers
cs.LG2026
Towards Identifiability of Interventional Stochastic Differential Equations
Aaron Zweig, Zaikang Lin, Elham Azizi +1
We study identifiability of stochastic differential equations (SDE) under multiple interventions. Our results give the first provable bounds for unique recovery of SDE parameters g…
cs.LG2026
Interpretable Neural ODEs for Gene Regulatory Network Discovery under Perturbations
Zaikang Lin, Sei Chang, Aaron Zweig +4
Modern high-throughput biological datasets containing thousands of perturbations enable large-scale discovery of causal graphs that represent regulatory interactions between genes.…