Masanari Shimura | Searcharxiv

arXiv2026

Eigenvalue degeneracy in sparse random matrices

In random matrices with independent and continuous matrix entries, the degeneracy probability of the eigenvalues is known to be zero. In this paper, random matrices including discontinuous matrix entries are analyzed in order to observe how degeneracy is generated. Using Erd\"os-R\'enyi matching probability theory of random bipartite graphs, we asymptotically evaluate the degeneracy probability of such random matrices. As a result, due to accumulation of the eigenvalues to the origin, a positive degeneracy probability is found for eigenvalues of a sparse random matrix model.

math-ph↗

arXiv2025

Enhancing AI System Resiliency: Formulation and Guarantee for LSTM Resilience Based on Control Theory

This paper proposes a novel theoretical framework for guaranteeing and evaluating the resilience of long short-term memory (LSTM) networks in control systems. We introduce "recovery time" as a new metric of resilience in order to quantify the time required for an LSTM to return to its normal state after anomalous inputs. By mathematically refining incremental input-to-state stability ($\delta$ISS) theory for LSTM, we derive a practical data-independent upper bound on recovery time. This upper bound gives us resilience-aware training. Experimental validation on simple models demonstrates the effectiveness of our resilience estimation and control methods, enhancing a foundation for rigorous quality assurance in safety-critical AI applications.

cs.AI↗