You can learn more about me over nyah!
My interests lie at the intersection of deep learning and reinforcement learning, with a strong focus on theoretical foundations. In deep learning, I am drawn to understanding why and how models work, spanning both training dynamics and architectural principles. In reinforcement learning, I am similarly motivated by formal frameworks, with a keen interest in classical RL theory.
- Reinforcement Learning
- Theoretical Reinforcement Learning
- Deep Reinforcement Learning
- Stochastic & Black-Box Optimization
- Trustworthy AI
- Adversarial Robustness
- Differential Privacy
- Explainable AI
- Geometric Deep Learning
- Machine Learning with Graphs
- Graph Neural Networks
- Deep Generative Models
- Diffusion Models & Flow Matching
- Optimal Transport
