I am an independent researcher working across mathematical statistics, machine learning, and time-series analysis. My work focuses on developing and analyzing methods that blend rigorous statistical theory with modern computational modeling, particularly for high-dimensional or structured data.

I am interested in collaborations involving theoretical analysis, modeling frameworks, and computational methodology motivated by real-world complex data.

• High-dimensional statistics
• Model selection and regularization
• Nonparametric and semiparametric inference
• Missing-data mechanisms (MAR/MNAR)
• Robustness and contamination models

• Empirical processes, concentration, and generalization
• Approximate inference: variational Bayes, MCMC, stochastic approximations
• Deep generative models: flows, diffusion models, energy-based models

• State-space models (linear, nonlinear, SSMs, SDEs)
• Diffusion-based forecasting
• Representation learning for sequential data

Languages:

Computational Frameworks:

Probabilistic Programming: NumPyro - Pyro - PyMC3

My work aims to build connections between:

• Statistical theory (empirical processes, concentration, asymptotics)
• Modeling and computation (variational inference, SDEs, diffusion-based models)
• Applications where structure and uncertainty play a central role (biostatistics, forecasting, high-dimensional regimes)

I am particularly motivated by methodologies that offer both statistical guarantees and practical applicability, and I enjoy collaborations where theory, computation, and application inform each other.