|
Diyang Li 李笛扬 [Email] [Google Scholar] [LinkedIn] |
I am a fourth-year Ph.D. student in the Department of Computer Science at Cornell University, where I am fortunate to be advised by Prof. Kyra Gan.
My research interests lie at the intersection of machine learning and large-scale optimization.
Broadly, I aim to develop efficient machine learning algorithms that come with both theoretical guarantees and solid empirical performance. I am particularly drawn to real-world settings or scenarios where computation is a bottleneck. I enjoy designing methods that make learning faster, more scalable, or more robust, while keeping them simple for practitioners to adopt. More recently, I have become interested in reasoning and test-time scaling for language models.
Prior to joining Cornell, I received my bachelor's degree from Nanjing University of Information Science & Technology in 2023. During my undergraduate, I was a visiting student in the Machine Learning Department at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI).
Research
- Efficient Fine-Tuning for Structured Sparsity Under Group Repartitioning
Diyang Li
Fortieth Conference on Neural Information Processing Systems (NeurIPS 2026) - Never Go Full Batch: Stochastic TMLE for Large-Scale Debiased Inference
Diyang Li, Fei Wang, Kyra Gan
Fortieth Conference on Neural Information Processing Systems (NeurIPS 2026) - Regularization Paths for Continuous DAG Learning
Diyang Li, Fei Wang, Kyra Gan
Fortieth Conference on Neural Information Processing Systems (NeurIPS 2026) - Federated Targeted Maximum Likelihood Estimation
Diyang Li, Fei Wang, Kyra Gan
Preprint manuscript, arXiv:2609.30503, 2026 - Targeted Maximum Likelihood Learning: An Optimization Perspective
Diyang Li, Kyra Gan
Thirty-Ninth Conference on Neural Information Processing Systems (NeurIPS 2025) - Learning No-Regret Sparse Generalized Linear Models with Varying Observation(s)
Diyang Li, Charles Ling, Zhiqiang Xu, Huan Xiong, Bin Gu
Twelfth International Conference on Learning Representations (ICLR 2024), Spotlight - Generalized Fast Exact Conformalization
Diyang Li
Thirty-Eighth Conference on Neural Information Processing Systems (NeurIPS 2024) - When Online Learning Meets ODE: Learning without Forgetting on Variable Feature Space
Diyang Li, Bin Gu
Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023) - GAGA: Deciphering Age-path of Generalized Self-paced Regularizer
Xingyu Qu*, Diyang Li*, Xiaohan Zhao, Bin Gu
Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS 2022), Spotlight - Chunk Dynamic Updating for Group Lasso with ODEs
Diyang Li, Bin Gu
Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022)
Program Committee
- International Conference on Machine Learning (ICML): 2022 - 2026
- Neural Information Processing Systems (NeurIPS): 2023 - 2026
- International Conference on Learning Representations (ICLR): 2024 - 2027
- International Conference on Artificial Intelligence and Statistics (AISTATS): 2023 - 2027
- AAAI Conference on Artificial Intelligence (AAAI): 2023 - 2027
- NeurIPS Workshop on Optimization for Machine Learning (OPT-ML): 2023 - 2026
