My research group works at the interface of Machine Learning, Statistics, and Optimization. We are interested in formalizing the process of learning, in analyzing the learning models, and in deriving and implementing the emerging learning methods. A significant thrust of our research is on developing theoretical and algorithmic tools for online prediction and decision-making. Our recent interests include understanding neural networks and overparametrized models, as well as foundations of reinforcement learning.
The research group currently focuses on:
- Statistical Learning: We study the problem of building a good predictor based on an i.i.d. sample. While much is understood in this classical setting, our current focus is on the Deep Learning models. In particular, we study various measures of complexity of neural networks that govern their out-of-sample performance. Our recent focus is on statistical and computational aspects of interpolation methods, as well as understanding the phenomenon of benign overfitting in overparametrized models.
- Online Learning: We aim to develop robust prediction methods that do not rely on the i.i.d. or stationary nature of data. In contrast to the well-studied setting of Statistical Learning, methods that predict in an online fashion are arguably more complex and nontrivial. This field has some beautiful connections to Statistical Learning and the theory of empirical processes.
- Reinforcement Learning and Decision Making: In these problems, data are collected in an active manner and feedback is limited. Our work focuses on understanding the sample complexity, on developing computationally efficient methods, and on building a bridge between supervised learning and decision making. Our recent work established a quantity (the decision-estimation coefficient) that governs the sample complexity of interactive decision making and RL. (course notes)