My primary research agenda is to develop a mathematical characterization of machine learning (ML) models, their learning/training behavior and the associated precision achieved by them. Towards this end, I study the two broad facets of ML: theory; through the eyes of tools from systems theory, statistics and optimization; and applied; by building AI/ML models to solve key problems in nuclear physics, material science, HPC and more recently climate. I have a strong publication record in the field of ML, HPC and scientific applications with a total of 51 publications. I also have a significant track record of grants and have been involved in 23 grant proposals, many of them multi-institutional. I also have substantial experience in successfully soliciting and managing multi-million dollar multi-institutional proposals as an institutional PI.
News
- Oct 2026 Grant awarded: An Active-Learning Prioritization Engine for Nuclear Data Relevant to X-Ray Bursts
- Sep 2026 New software release: APEIRON — a continual learning harness for scientific applications
- Jul 2026 New research topic: Partially Observable Multi-Agent Reinforcement Learning
- Jul 2026 New software release: coadapt-marl — a decentralized multi-agent RL harness under partial observability
- Jun 2026 New journal paper: Kiso: A Foundation for Complex, Agentic, and Reproducible Experiments