Yifang Chen 陈一方
About Me
I am currently a fifth-year Ph.D. student in Computer Science and Engineering at the University of Washington. I am fortunate to be advised by Prof. Kevin Jamieson and Prof. Simon Shaolei Du.
My research focuses on algorithmic data-and-label-efficient learning from both empirical and theoretical perspectives. Specifically:
Empirical side: I investigate how to curate data in an open-world setting to train general-purpose large models and design label-efficient algorithms to adapt pretrained models to specific downstream tasks.
Theoretical side: I design online/active learning algorithms beyond the well-specified setting and combine them with deep representation learning theory.
Check out our website LabelTrain.ai, an ongoing open-source project for experimentally exploring the strengths and weaknesses of label-efficient learning algorithms.
In my early years, I designed practical and adaptive machine learning algorithms with strong theoretical guarantees, focusing on corrupted and non-stationary online decision-making settings.
Prior to starting my Ph.D., I completed my master's and undergraduate degrees in Electrical Engineering at the University of Southern California, advised by Prof. Haipeng Luo. I want to especially thank him and my colleague Chen-Yu Wei, who introduced me to the world of learning theory.
I am on the job market this year! Looking for both industrial and academic opportunities!
Research Interests
Active learning, data selection, experimental design
Representation learning
Online learning, bandits, Reinforcement learning theory
Experimental design for scientific applications
Selected Publications
[NeurIPS24] CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning. (Spotlight)
Yiping Wang*, Yifang Chen*, Wendan Yan, Alex Fang, Wenjin Zhou, Simon Du, Kevin Jamieson.
[ACLFindings24] Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models.
Gantavya Bhatt*, Yifang Chen*, Arnav M. Das*, Jifan Zhang*, Sang T. Truong, Stephen Mussmann, Yinglun Zhu, Jeffrey Bilmes, Simon S. Du, Kevin Jamieson, Jordan T. Ash, Robert D. Nowak
[Journal of DMLR] LabelBench: A Comprehensive Framework for Benchmarking Label-Efficient Learning. [Github]
Jifan Zhang*, Yifang Chen*, Gregory Canal, Stephen Mussmann, Yinglun Zhu, Simon Shaolei Du, Kevin Jamieson, Robert D Nowak
[ICML22] Active Multi-Task Representation Learning.
Yifang Chen, Simon Du, Kevin Jamieson.
[ICML22] First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach. (Long presentation)
Andrew Wagenmaker, Yifang Chen, Max Simchowitz, Simon S. Du, Kevin Jamieson
[ICML’21] Improved corruption robust algorithms for episodic reinforcement learning.
Yifang Chen, Simon Du, Kevin Jamieson.
[COLT’19] A new algorithm for non-stationary contextual bandits: Efficient, optimal and parameter-free.
Yifang Chen, Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei
|