# Postdoctoral Fellowship: MSPRF: Statistical Theory and Methods for Sparse Mixture-of-Experts

> **NSF 01002627DB NSF RESEARCH & RELATED ACTIVIT** · Al-Ghattas, Omar Hussein (MA) · $190,000

## Abstract

This award is made as part of the FY 2026 Mathematical Sciences Postdoctoral Research Fellowships Program. Each of the fellowships supports a research and training project at a host institution in the mathematical sciences, including applications to other disciplines such as Artificial Intelligence and Quantum Information Science, under the mentorship of a sponsoring scientist.

The title of the project for this fellowship to Omar Al-Ghattas is “Statistical Theory and Methods for Sparse Mixture-of-Experts”. The host institution for the fellowship is the Massachusetts Institute of Technology and the sponsoring scientist is Philippe Rigollet.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

## Key facts

- **NSF award ID:** 2602099
- **Awardee organization:** Al-Ghattas, Omar Hussein (MA)
- **PI:** Omar H Al-Ghattas
- **Primary program:** 01002627DB NSF RESEARCH & RELATED ACTIVIT
- **All programs:** Artificial Intelligence (AI), Machine Learning Theory, POSTDOCTORAL FELLOWSHIPS IN MATH SCIENCE
- **Estimated total:** $190,000
- **Funds obligated:** $190,000
- **Transaction type:** Fellowship Award
- **Period:** 09/01/2026 → 08/31/2030

## Primary source

NSF Award Search: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2602099

## Citation

> US National Science Foundation, Award 2602099, Postdoctoral Fellowship: MSPRF: Statistical Theory and Methods for Sparse Mixture-of-Experts. Retrieved via AI Analytics 2026-06-08 from https://api.ai-analytics.org/grant/nsf/2602099. Licensed CC0.

---

*[NSF Awards dataset](/datasets/nsf-awards) · CC0 1.0*