Research Interests

My research focuses on high-dimensional and structured learning at the intersection of statistical machine learning, information processing, and quantum computing. I develop theoretically grounded, efficient frameworks for advancing both next-generation intelligent systems and hybrid quantum-classical computing architectures, bridging foundational theory with practical implementation.

My long-term research program aims to establish a unified framework for learning and information processing in high-dimensional classical and quantum systems. The central goal is to develop a cohesive theory and algorithmic toolkit that enables both principled understanding and practical application across classical and quantum computational paradigms.

I develop theoretical foundations and algorithmic tools for structured learning.

• Algorithm Design & Analysis: Provable methods for high-dimensional structured learning and estimation
• Theoretical Understanding: Principles for designing and analyzing structured models underlying learning and information processing
• Structured Representations: Exploiting low-rank, sparse, manifold, and tensor-network structures in data

I translate these insights to address challenges in emerging computational paradigms.

• Quantum Learning & Information: Hybrid classical-quantum computing architectures
• Modern AI Architectures: Deep neural networks, Transformers, and in-context learning
• Intelligent Signal Processing: Communication and sensing systems