2025/11/12 by Isshin Arai, Arai, Isshin, Tomoaki Itano +1
Computer Science · Mathematics · Physics and Astronomy · #FOS: Physical sciences #Gaussian Processes and Bayesian Inference #Mathematical Physics (math-ph) #Model Reduction and Neural Networks #Tensor decomposition and applications
paper · pdf · doi:10.48550/arxiv.2511.08995
openalex publication_date 2025/11/12 · openalex created_date 2025/11/14 · openalex updated_date 2026/07/28
In physical systems possessing symmetry, reconstructing the underlying causal structure from observational data constitutes an inverse problem of fundamental importance. In this work, we formulate the inverse problem of causal inference within the framework of group-representation theory, clarifying the structure of the representation spaces to which the \it causality and estimation maps belong. This formulation leads to both theoretical and practical limits of reconstructability (identifiability). We show that the local velocity-gradient tensor, regarded as a \it causal factor, can be reconstructed from the orientational motion of suspended particles. In this setting, the estimation map must act as a group homomorphism between the observation and causal spaces, and the reconstructable subspace is constrained by the decomposition structure of the SO(3) representation. Based on this principle, we construct an SO(3)-equivariant neural network (implemented with the e3nn framework) and verify that the identifiability determined by the group-representation structure is reproduced in the actual learning process. These results demonstrate a fundamental principle that the group-representation structure determines the reconstructability (identifiability limit) in inverse problems of causal inference.