4 papers
Joint Lyapunov Certificates for K-Agent Generative AI Governance: Stochastic Stability, Emergent Ensemble Risk, and Zero-Knowledge Governance Attestation
Sriram Nagaraj
We develop a rigorous mathematical framework for the governance of systems of K self-adapting generative AI models under the principles of Model Risk Management (MRM). When multipl…
Telemetry and Concealment in Self-Adapting Generative AI: Logging Architecture, Adversarial Model Hiding, and the Limits of Detection
Sriram Nagaraj
Model risk management (MRM) guidance assumes a static model lifecycle, in which models are developed, independently validated, and implemented without further autonomous modificati…
Recursive Governance: A Graph-Theoretic Framework for Risk Propagation and Drift Detection in Agentic AI Systems
Sriram Nagaraj, Advaith Nila Narayanan
As financial institutions transition from traditional predictive models to autonomous agentic systems, the static model inventory requirements of traditional model risk management…
Nonlocal Neural Tangent Kernels via Parameter-Space Interactions
Sriram Nagaraj, Vishakh Hari
The Neural Tangent Kernel (NTK) framework has provided deep insights into the training dynamics of neural networks under gradient flow. However, it relies on the assumption that th…