Yuwen Huang’s homepage
Information Theory · Statistical Physics · Optimization · Quantum Information
Structured inference and optimization with rigorous guarantees
Recruiting RAs, MPhil/PhD students, and Postdocs
I am building a research group on graphical models, inference, optimization, machine learning, and quantum information, with an emphasis on mathematically rigorous ideas that lead to scalable algorithms.
I welcome applications and inquiries from research assistants, MPhil students, PhD students, and Postdocs who are excited by theory-driven work with algorithmic and systems impact.
How to apply
Please send a concise email introducing your background and interests, together with the materials below.
[RA Application] Your Name - Current Institution [MPhil Inquiry] Your Name - Current Institution [PhD Inquiry] Your Name - Current Institution [Postdoc Application] Your Name - Current InstitutionRA / MPhil / PhD
Include a short motivation note in the email body, plus your CV and transcript.
Postdoc
Include your CV and a short research statement describing your interests and future agenda.
What I provide
RA
- Close research mentoring in structured inference, optimization, and graphical models.
- Hands-on exposure to mathematically grounded algorithm design and analysis.
- Preparation for MPhil/PhD study or algorithm-focused industry roles.
MPhil
- A structured transition from coursework into independent research problems.
- Training that combines theory, applications, and rigorous performance guarantees.
- Preparation for PhD study or advanced R&D roles in data science and systems.
PhD
- Ownership of deeper research directions at the interface of theory, algorithms, and systems.
- Opportunities to publish, collaborate broadly, and build an academic research profile.
- Preparation for academic positions or long-term research careers.
Postdoc
- Support for building an independent research agenda and publication leadership.
- Opportunities to co-mentor students and shape a growing research group.
- Preparation for academic job searches and broader collaboration networks.
I am a postdoctoral researcher at CUHK developing provable and scalable methods for inference, counting, and optimization in structured systems. My work brings together probabilistic graphical models, Bethe and graph-cover methods, combinatorics, tensor-network representations, and distributed quantum computation to turn mathematical structure into practical algorithms with rigorous guarantees.
Current work
Structure-aware inference, combinatorial counting, optimization, and distributed quantum computation.
Future direction
Bringing structure-aware inference and optimization into machine learning, learning theory, and quantum information processing.
Theory to Impact
Theory
information theory · statistical physics
Algorithms
Inference, counting, and optimization with structure and guarantees
Systems
distributed quantum platforms
Impact
machine learning and efficient computation
Research Directions
Selected directions and representative papers:
Probabilistic graphical models
Bethe approximations, graph covers, and message passing for principled inference and counting.
Optimization and decision-making
Structure-exploiting optimization and permanent bounds with provable guarantees.
Tensor networks and quantum-enabled methods
Tensor-network representations and quantum-enabled methods for compact, high-dimensional computation.
Distributed quantum computing and networks
Distributed quantum architectures for large-scale optimization, inference, and data-intensive analytics.