arXiv stat.ML
· Papers
Learning Bidirectional Causal Interactions with Heteroscedastic Neural Networks
arXiv:2607.22313v1 Announce Type: new Abstract: Estimating contemporaneous bidirectional interactions from observational data is difficult because each outcome is endogenous to the other, while flexible regressions may capture only reduced-form dependence. This paper proposes SEM-DNN, a heteroscedastic neural simultane