Scholar
Siyu Chen
Google Scholar ID: S1tCv5MAAAAJ
Ph.D. of S&DS, Yale University
Citations & Impact
Citations
212
H-index
8
i10-index
8
Publications
15
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Chen, S., Yang, D., Li, J., Wang, S., Yang, Z., & Wang, Z. (2022). Adaptive model design for Markov decision process. In International Conference on Machine Learning, 3679–3700. PMLR.
- Chen, S., Wang, M., & Yang, Z. (2023). Actions Speak What You Want: Provably Sample-Efficient Reinforcement Learning of the Quantal Stackelberg Equilibrium from Strategic Feedbacks. arXiv Preprint arXiv:2307.14085.
- Chen, S., Wang, Y., Wang, Z., & Yang, Z. (2023). A unified framework of policy learning for contextual bandit with confounding bias and missing observations. arXiv Preprint arXiv:2303.11187.
- Sheen, H., Chen, S., Wang, T., & Zhou, H. H. (2024). Implicit Regularization of Gradient Flow on One-Layer Softmax Attention. Presented at ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning.
- Zhang, Y*., Chen, S*., Yang, Z., Jordan, M., & Wang, Z. (2021). Wasserstein flow meets replicator dynamics: A mean-field analysis of representation learning in actor-critic. In Advances in Neural Information Processing Systems, 34, 15993–16006.
- Chen, S., Wu, J., Wu, Y., & Yang, Z. (2023). Learning to incentivize information acquisition: Proper scoring rules meet principal-agent model. In International Conference on Machine Learning, 5194–5218. PMLR.
- Chen, S., Sheen, H., Wang, T., & Yang, Z. (2024a). Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality. In The Thirty Seventh Annual Conference on Learning Theory (pp. 4573-4573). PMLR.
- He, J*., Chen, S*., Zhang, F., & Yang, Z. (2024). From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems. In International Conference on Machine Learning, 5194–5218. PMLR.
- Wu, J., Chen, S., Wang, M., Wang, H., & Xu, H. (2024). Contractual Reinforcement Learning: Pulling Arms with Invisible Hands. arXiv Preprint arXiv:2407.01458.
- Hu, X., Zhang, F., Chen, S., & Yang, Z. (2024). Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods. arXiv Preprint arXiv:2408.14511.
- Chen, S*., Sheen, H*., Wang, T., & Yang, Z. (2024b). Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers. arXiv Preprint arXiv:2409.10559.
Research Experience
- Currently pursuing a Ph.D. in Statistics at Yale University, working on multiple research projects.
Education
- Ph.D., Statistics & Data Science, Yale University, 2022—2027 (expected); B.E., Electronic Engineering, Tsinghua University, 2018—2022.
Background
- Research interests include deep learning, foundation models, various aspects of statistics, and reinforcement learning.
Miscellany
- Email: siyu.chen.sc3226@yale.edu
Co-authors