Sridhar Mahadevan


Research Professor

Director, Adobe Research

AAAI Fellow

Co-Director, Autonomous Learning Laboratory

Research Interests

Artificial Intelligence

Category Theory

Machine Learning

Variational Inequalities


firstname.i.lastname AT gmail

Administrative Assistant: Sarah Byrne

My current research involves the application of category theory to construct universal models of intelligence, from causality, creativity and imagination, to decision making and learning. A universal property of an object c in a category C is a representable functor F that has a natural isomorphism with the set of all morphisms into c, namely Hom(-, c) given by the Yoneda Lemma. See my recent papers on universal causal inference and universal decision making.

Selected Recent Papers and Talks

Sridhar Mahadevan, On the Universality of Causal Diagrams and the Causal Reproducing Property, Arxiv, July 2022

Sridhar Mahadevan, Universal Decision Models ( (download slides), Invited Talk, Indian Institute of Science, October 23rd, 2021

Sridhar Mahadevan, Universal Decision Models, Arxiv, 2021

Sridhar Mahadevan, Asymptotic Causal Inference, Arxiv, 2021.

Sridhar Mahadevan, Causal Homotopy, Arxiv, 2021.

Sridhar Mahadevan, Causal Inference in Network Economics, Arxiv, 2021.

Sridhar Mahadevan, Anup Rao, Jennifer Healey, Georgios Theocharous, Multi-scale Manifold Warping, Arxiv, 2021.

Sridhar Mahadevan, New Directions in Planning, Tutorial, International Conference on Automated Scheduling and Planning Systems (ICAPS), 2020.

Machines Who Imagine: Beyond Data Science, Tutorial at ECML Conference, September 16 2019. Wurzburg, Germany.