17 papers
Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability
Amir Asiaee
Mechanistic interpretability often evaluates explanations by intervening on a model: swapping hidden states, patching activations, ablating components, or comparing a compressed mo…
Workload-Preserving Differentially Private Synthetic Data for Causal Inference via Maximum-Entropy Calibration
Amir Asiaee, Kaveh Aryan
Workload-based differentially private (DP) synthetic data methods privately measure aggregate queries and post-process the noisy answers into synthetic records. Generic workloads c…
Improving RCT-Based Treatment Effect Estimation Under Covariate Mismatch via Calibrated Alignment
Amir Asiaee, Samhita Pal
Randomized controlled trials (RCTs) are the gold standard for estimating treatment effects, yet they are often underpowered for detecting effect heterogeneity. Large observational…
Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions
Amir Asiaee, Kavey Aryan, James P. Long
Selective conformal prediction can yield substantially tighter uncertainty sets when we can identify calibration examples that are exchangeable with the test example. In interventi…
Improving Precision of RCT-Based CATE Estimation using Data Borrowing with Double Calibration
Amir Asiaee, Chiara Di Gravio, Cole Beck +3
Understanding how treatment effects vary across patient characteristics is essential for personalized medicine, yet randomized controlled trials (RCTs) are often underpowered to de…
Causal Mechanism Reduction: Mechanism Replacement for Neural Network Pruning and Abstraction
Amir Asiaee
Which internal mechanisms of a neural network can be replaced while preserving the computation it performs? Structured pruning asks for smaller deployable networks; causal abstract…