works on

From the 2 of 13 linked papers with an AI index.

collaborators

13 papers

cs.LG2026

Learning in Infinitesimal Non-Compositional Sketches

Sridhar Mahadevan

The paper proposes a categorical framework called LINCS that models machine learning problems as sketches and addresses non‑compositionality by lifting these sketches to tangent ca…

cs.LG2026

Agentic Skill Optimization over Lie Algebroids

Sridhar Mahadevan

The paper introduces LASKO, a Lie algebroid‑based framework for optimizing agentic skill edits (e.g., prompts, rubrics) by modeling edit policies as sections of a controlled Lie al…

cs.AI2026

Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models

Sridhar Mahadevan

We introduce a categorical framework called ODYSSEY for constructing verifiable, local truth-preserving foundation models as compositions of foundries: building-block architectural…

math.CT2026

Infinitesimal Causality

Sridhar Mahadevan

Interventions can be varied continuously in many causal models. Differentiating a specified smooth intervention protocol produces vector fields on a statistical model, and their Li…

cs.LG2026

Latent Confounded Causal Discovery via Lie Bracket Geometry

Sridhar Mahadevan

We study causal discovery from observational and interventional regimes when latent variables may affect the measured system. Our first algorithm, BRIDGE (Bracket Residuals for Int…

stat.ME2026

Causal Density Functions

Sridhar Mahadevan

We study the full density ratio between a specified intervention regime and an observational regime , , under the prerequisite . We call the…