Overview
Quantum machine learning (QML) sits at the intersection of quantum computing and artificial intelligence, promising exponential speedups for certain learning tasks and novel capabilities unavailable to classical machine learning.
My research group has made foundational contributions to QML theory and practice, from establishing the expressive power of quantum neural networks to pioneering quantum generative adversarial networks with experimental demonstrations. We've identified and addressed critical challenges such as barren plateaus that threaten the trainability of deep variational quantum circuits.
Our work spans theoretical analysis (expressivity, trainability, learnability), algorithm design (QNNs, QGANs, quantum kernel methods), and practical applications (chemistry, optimization, pattern recognition). With over 20 publications in this area and collaborations with leading machine learning researchers, we're advancing both the foundations and applications of quantum-enhanced learning.
Research Goals
- Understand QNN expressivity and trainability — Establish theoretical foundations for when and why quantum neural networks outperform classical counterparts
- Address barren plateau challenges — Develop initialization strategies and architecture designs that enable training of deep variational quantum circuits
- Design practical quantum learning algorithms — Create QML protocols that demonstrate advantage on realistic near-term devices
- Bridge quantum learning and applications — Apply QML to real-world problems in chemistry, optimization, and data analysis
Collaborators Network Map
Global collaborators across Quantum Machine Learning institutions.
All Co-authors in Selected Publications
Alphabetical by Last Name
Selected Publications
Last curated: —