Governance, serverless, and automation facilitate enterprise integration that is adaptive, cost-effective, low-code, and capable of creating dynamic, context-aware, and value-adding workloads. This creates a need for policy-based management that simplifies implementation in multicloud scenarios. Serverless automation, enabled by event-driven workloads and dynamic resource provisioning for short-lived tasks, can operate in multicloud environments without being controlled by any provider. Introducing artificial intelligence facilitates improvements in scheduling and resource optimization. However, these benefits are not well understood, nor are these ecosystems properly managed. What governance is required for such serverless automation in an AI-enable enterprise integration setting? What does governance in serverless environments achieve? These questions are addressed through a structured research-product approach. The concept of serverless automation is first established, then applied to governance and a serverless context.A critical perspective on governance emerges through examination of central concepts and their interplay within a formal control-compliance-risk framework. From a practical angle, governance focuses on preserving trust in business operation and service delivery. This leads to the consideration of a Cloud Automation Control Plane that governs the core events and processes of Cloud Automation on behalf of initiation parties. The enterprise integration layer can be made serverless to minimize code development, improve resilience, and enhance security with AI assistance. The AI inclusion can be exploited for intelligent workload and resource management without compromising the governing principles. These avenues in combination demonstrate that a clear governance model can enable sustainable Cloud AI Automation for the enterprises and the ecosystem.
Sridhar Mahadevan· International journal of com...· 0 citations
This paper develops a categorical framework -- Learning in Infinitesimal Non-Compositional Sketches (LINCS) -- as the repair of non-compositionality: failures of diagrams to factor through quotient sketches lifted to the tangent category setting. Machine learning problems are specified as sketches: graphs with commutativity conditions $\mathcal D$, limit cones $\mathcal L$, and colimit cocones $\mathcal K$, generalizing the usual scalarization of loss functions or vector space assumptions. Non-compositionality is defined purely as failure of a universal factorization problem, not as arithmetic error between the desired and actual predictions. Given a learning sketch $\mathbb S=(S,\mathcal D,\mathcal L,\mathcal K)$, whose underlying graph is $S$, and a model $D:J \rightarrow C$, the base defect is the obstruction to factorization $\mbox{Obs}(\mbox{Fact}_{\mathbb S}(D))$. The tangent lift applies the tangent functor $T$ to obtain $TD:J \rightarrow C$, and LINCS is defined as the obstruction $\mbox{Obs}(\mbox{Fact}_{\mathbb S}(TD))$ -- asking whether infinitesimal perturbations preserve the compositionality constraints.The paper also introduces Tangent Learning Sketches, which are sketches equipped with Cockett-Cruttwell tangent structure. The paper defines the INC endofunctor, which iterates the tangent lift, producing a tower $D,TD,T^2D, \cdots$ of factorization problems. ML is thereby formulated as the search for a coalgebraic fixed point where successive tangent unfoldings stabilize ($\nu T_{\mbox{INC}}$). Using the Aczel--Mendler theorem, we prove existence of a final INC coalgebra whenever $T_{\mbox{INC}}$ admits a set-based class realization that creates its final carrier. A detailed experimental evaluation of LINCS is underway in a number of concrete ML settings, including deep learning, large language models, and reinforcement learning, and is described in companion papers.
Sridhar Mahadevan· arXiv.org· 2 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
