All research directions
ML/DL Theory
Kernel methods, optimization theory, and convergence analysis for modern deep learning.
Goals
To establish the theoretical foundations that explain how and why machine learning algorithms work, from kernel embeddings to optimizer dynamics.
Overview
This direction bridges classical machine learning theory with the training dynamics of deep networks. It spans kernel methods, large-scale optimization, Wasserstein distances, and principled analysis of learning rates and convergence.
Key objectives
- Characterize optimizer dynamics and convergence behavior
- Advance kernel methods for high-dimensional learning
- Develop online and streaming algorithms with guarantees
- Connect classical theory with modern deep learning practice
Key topics
- Kernel methods and reproducing kernel Hilbert spaces
- Optimization and convergence analysis
- Wasserstein and optimal transport in ML
- Online and streaming learning
Papers in this direction
Spectral Flattening Is All Muon Needs: How Orthogonalization Controls Learning Rate and Convergence
Nguyen, TP, Nguyen, T, Truong, MP, Nguyen, T, Bailey, J, Le, T
arXiv preprint arXiv:2605.13079
A Unified Wasserstein Distributional Robustness Framework for Adversarial Training
Le, T, Nguyen, T, Phung, D
International Conference on Learning Representations (ICLR)