I am an assistant professor in the Department of Electrical and Computer Engineering at the University of California, Riverside. In 2023, I got my Ph.D. in Computer Sciences at the University of Wisconsin–Madison, where I was fortunate to be advised by Robert Nowak. In 2021, I spent a wonderful summer at Microsoft Research NYC, working with Paul Mineiro, Dylan Foster, and John Langford.

I work on interactive machine learning (e.g., active learning, bandits, and reinforcement learning), where my goal is to develop efficient human-in-the-loop learning algorithms and systems. Recently, I became interested in connecting interactive machine learning with large models (e.g., large language models), from both algorithmic and systemic perspectives. Specifically, some research topics I would like to further explore include:

• Data selection and generation for large models

• LLM-powered interactive learning agents and systems

• Efficient training and inference systems for large models

• AI safety and alignment (e.g., using reinforcement learning)

• Theoretical foundations of transformer / attention / interactive ML

\(\bigstar\) Prospective Students. I am actively looking for Ph.D. students and visitors/interns who are generally interested in Machine Learning and/or Machine Learning Systems. If you are interested in joining my lab, please (i) fill out this form and (ii) drop me an email with you CV and transcripts.

Teaching

• Spring 2024: EE 260 Large Models and Advances in AI

• Fall 2023: EE/CS 228 Introduction to Deep Learning

Publications

• Infinite Action Contextual Bandits with Reusable Data Exhaust
  Mark Rucker, Yinglun Zhu, and Paul Mineiro
  International Conference on Machine Learning (ICML) 2023

• Active Learning with Neural Networks: Insights from Nonparametric Statistics
  Yinglun Zhu and Robert Nowak
  Conference on Neural Information Processing Systems (NeurIPS) 2022

• Efficient Active Learning with Abstention
  Yinglun Zhu and Robert Nowak
  Conference on Neural Information Processing Systems (NeurIPS) 2022

• Contextual Bandits with Large Action Spaces: Made Practical
  Yinglun Zhu, Dylan Foster, John Langford, and Paul Mineiro
  International Conference on Machine Learning (ICML) 2022, [Code], [Spotlight talk, 6 min]
  \(\bigstar\) Now available at the leading machine learning library Vowpal Wabbit (see here for instructions) and commercially incorporated into Microsoft Azure Personalizer!

• Contextual Bandits with Smooth Regret: Computational Efficiency in Continuous Action Spaces
  Yinglun Zhu and Paul Mineiro
  International Conference on Machine Learning (ICML) 2022, [Code]
  \(\bigstar\) Selected for a full oral presentation (top 2.1%), [Oral talk, 17 min]

• Near Instance Optimal Model Selection for Pure Exploration Linear Bandits
  Yinglun Zhu, Julian Katz-Samuels, and Robert Nowak
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2022, [Code]

• Pareto Optimal Model Selection in Linear Bandits
  Yinglun Zhu and Robert Nowak
  International Conference on Artificial Intelligence and Statistics (AISTATS) 2022, [Code]

• Pure Exploration in Kernel and Neural Bandits
  Yinglun Zhu\(^\star\), Dongruo Zhou\(^\star\), Ruoxi Jiang\(^\star\), Quanquan Gu, Rebecca Willett, and Robert Nowak
  Conference on Neural Information Processing Systems (NeurIPS) 2021, [Code]

• On Regret with Multiple Best Arms
  Yinglun Zhu and Robert Nowak
  Conference on Neural Information Processing Systems (NeurIPS) 2020, [Code]

• Robust Outlier Arm Identification
  Yinglun Zhu, Sumeet Katariya, and Robert Nowak
  International Conference on Machine Learning (ICML) 2020, [Code]