MIT iQuHack Quantum Hackathon
Led team to build an ML system predicting optimal quantum circuit simulation parameters, achieving 85% accuracy and 46-51% performance gains over baseline.
Quantum Computing Machine Learning Python LightGBM
Overview
Built an ML system that predicts optimal quantum circuit simulation parameters without running simulations, achieving 85% accuracy and 46-51% performance gains over baseline.
Technical Approach
- Engineered automated feature extraction pipeline from OpenQASM circuits
- Developed ensemble prediction system comparing 4 architectures: LightGBM, Gaussian Process Regression, curve predictors, and baseline models
- Team leader role at MIT’s iQuHack hackathon (January–February 2026)