• image

    Theoretical Foundation of Machine Learning

    This research topic is to study the mathematical theory of machine learning algorithms. For example, the mathematical models for deep neural networks and overparameterized models, bandit algorithms and sample efficient reinforcement learning.

  • image

    Efficient Computational Algorithms

    This research topic is concerned with efficient convex and nonconvex optimization, sampling methods, large scale and distributed training, automatic tuning of machine learning models.

  • image

    Robust and Adaptive Methods

    This research topic is concerned with the generalization of machine learning procedures to new scenarios, and related issues of distribution shift. We consider problems such as effective adaptation of ML models to new domains, unsupervised pretraining and fine-tuning, multi-objective learning, corruption and misspecified models, and exploration issues in reinforcement learning.

  • image

    Generative AI and Large Language Models

    This research topic is to study generative AI, including gradient based generative models, and issues related to large language models such as prompt engineering, data quality in training, optimization, reasoning, and RLHF.