Research

My research focuses on optimization, meta-learning, high-dimensional statistics, in-context learning, and transformers, with applications in machine learning and deep learning. I am particularly interested in understanding the theoretical foundations of machine learning algorithms and developing efficient, scalable methods for large-scale and high-dimensional data. My work explores how gradient-based optimization techniques and statistical inference methods can enhance the reliability and performance of AI models. Additionally, I have a growing interest in causal inference for deep learning, aiming to improve model interpretability and robustness. By bridging theory with practical applications, I seek to develop innovative machine learning frameworks that contribute to both academia and industry.