Global Identifiability of L1-based Dictionary Learning via Matrix Volume Optimization
Establishes global identifiability guarantees for L1-based dictionary learning via a matrix-volume formulation.
Applied Scientist at Amazon
Jingzhou Hu.
From identifiable representations
to adaptive decision-making.
I work on machine learning foundations and LLM-based systems, with interests in representation learning, optimization, and adaptive decision-making.
Research & applied sciencePh.D. · University of Florida
Selected publications
Identifiable Bounded Component Analysis via Minimum Volume Enclosing Parallelotope
Introduces a minimum-volume enclosing parallelotope view for identifiable bounded component analysis.
Complex Bounded Component Analysis: Identifiability and Algorithm
Provides identifiability analysis and an efficient algorithm for complex-valued bounded component analysis.
Research interests
- Machine learning foundations
- Identifiable representation learning, latent variable models, and non-convex optimization.
- Adaptive decision systems
- Contextual neural bandits, learning from partial feedback, and uncertainty-aware decisions.
- LLM & agentic reasoning
- Routing, orchestration, evaluation, and control for systems built on large language models.
Background
About me.
I am an Applied Scientist at Amazon, working on LLM-based agentic reasoning systems and adaptive decision-making pipelines.
I received my Ph.D. in Computer Science from the University of Florida, advised by Prof. Kejun Huang. Before joining UF, I received my bachelor’s degree from Nanjing University.
Connect on LinkedIn