Amortized transformer model with conditional fixed-point iterations learns SCM causal mechanisms from data and graphs, matching per-dataset baselines and outperforming in low-data regimes.
The models were trained for a total of 10k epochs with the Adam optimizer [Paszke et al., 2017], where we used a learning rate of 1e − 4 and a weight decay of 5e −
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Amortized Inference of Causal Models via Conditional Fixed-Point Iterations
Amortized transformer model with conditional fixed-point iterations learns SCM causal mechanisms from data and graphs, matching per-dataset baselines and outperforming in low-data regimes.