About Me

I am a second-year Ph.D. student in Computer Science and Engineering Department at University of California San Diego (UCSD). I’m fortunate to be advised by Prof. Tsui-Wei (Lily) Weng. I received my M.S. degree from UCSD and B.E. degree from Xi’an Jiaotong University.

[Google Scholar] [Twitter] [Zhihu]

Research Interests

My current research interests are theoretical machine learning and its applications, with a focus on deep learning theory (optimization, generalization, and robustness). My research goal is to establish theoretical foundations for modern deep learning models and develop principled algorithms for real-world applications.

Interested topics:

• Deep learning theory (optimization, generalization, robustness)
• Theory for large language models and foundation models
• Principled algorithms for real-world applications

Feel free to drop me an email if you would like to collabrate or have a discussion!

Publications

Machine Learning Theory

• Cross-Task Linearity Emerges in the Pretraining-Finetuning Paradigm.
  Zhanpeng Zhou¹, Zijun Chen¹, Yilan Chen, Bo Zhang, Junchi Yan.
  arXiv 2024.

• Analyzing Generalization of Neural Networks through Loss Path Kernels. [slides] [poster] [video]
  Yilan Chen, Wei Huang, Hao Wang, Charlotte Loh, Akash Srivastava, Lam M. Nguyen, Tsui-Wei Weng.
  Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023).

• Analyzing Deep PAC-Bayesian Learning with Neural Tangent Kernel: Convergence, Analytic Generalization Bound, and Efficient Hyperparameter Selection.
  Wei Huang¹, Chunrui Liu¹, Yilan Chen, Richard Yi Da Xu, Miao Zhang, Tsui-Wei Weng.
  Transactions on Machine Learning Research (TMLR 2023).

• On the Equivalence between Neural Network and Support Vector Machine. [code][slides][poster][video]
  Yilan Chen, Wei Huang, Lam M. Nguyen, Tsui-Wei Weng.
  Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021).

Interpretable Machine Learning

• The Importance of Prompt Tuning for Automated Neuron Explanations.
  Justin Lee¹, Tuomas Oikarinen¹, Arjun Chatha, Keng-Chi Chang, Yilan Chen, Tsui-Wei Weng.
  NeurIPS 2023 Workshop on Attributing Model Behavior at Scale.

• Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification.
  Quanshi Zhang¹, Xu Cheng¹, Yilan Chen, Zhefan Rao.
  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2023).

• Explaining Knowledge Distillation by Quantifying the Knowledge.
  Xu Cheng, Zhefan Rao², Yilan Chen², Quanshi Zhang.
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2020).

Invited Talks

Analyzing Generalization of Neural Networks through Loss Path Kernels [slides]

• Jan 2024 - ByteDance
• Nov 2023 - AI TIME

Teaching

• DSC 140B: Representation Learning, TA, Spring 2024
• DSC 210: Numerical Linear Algebra, TA, Fall 2023
• DSC 291: Trustworthy Machine Learning, Tutor, Fall 2021

Professional Service

• Conference Reviewer: ICML (2022, 2023, 2024), NeurIPS (2022), ICLR (2022)
• Journal Reviewer: Journal of Optimization Theory and Applications (JOTA)

Contact

University of California San Diego, La Jolla, CA
Email: yilan [at] ucsd.edu