4 papers
stat.ML2026
The Causal Description Gap: Information-Theoretic Separations Across Pearl's Hierarchy
Seyed Morteza Emadi
Pearl's causal hierarchy shows that observational, interventional, and counterfactual queries are qualitatively distinct. We ask a quantitative version of this question: how many a…
cs.LG2026
Rank-Aware Spectral Bounds on Attention Logits for Stable Low-Precision Training
Seyed Morteza Emadi
Attention scores in transformers are bilinear forms whose maximum magnitude governs overflow risk in low-precision training. We derive a \emp…
cs.LG2026
Exact Attention Sensitivity and the Geometry of Transformer Stability
Seyed Morteza Emadi
We develop a sensitivity analysis for transformer attention in a geometry aligned with tokenwise computation. Our main result is the exact identity …
stat.ML2026
The Critical Horizon: Inspection Design Principles for Multi-Stage Operations and Deep Reasoning
Seyed Morteza Emadi
Manufacturing lines, service journeys, supply chains, and AI reasoning chains share a common challenge: attributing a terminal outcome to the intermediate stage that caused it. We…