Temporal Causal Prior-Data Fitted Networks for Panel Data with Learned Reliability Signals
Shravan Talupula, Saurabh Sharma
cs.LG, stat.ML
Submitted: 2026-06-18
Comments: 42 pages, 6 figures, 9 tables. Code and pretrained checkpoint to be released
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Foundation Models for Causal Inference via Prior-Data Fitted Networks
- Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference
- Do-PFN: In-Context Learning for Causal Effect Estimation
- Interventional Time Series Priors for Causal Foundation Models
- Towards Continuous-time Causal Foundation Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks