Siyu Chen

According to our database, Siyu Chen authored at least 14 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders.

Siyu Chen, Heejune Sheen, Xuyuan Xiong, Tianhao Wang, Zhuoran Yang

CoRR, June, 2025

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model.

Siyu Chen, Beining Wu, Miao Lu, Zhuoran Yang, Tianhao Wang

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods.

Xinyang Hu, Fengzhuo Zhang, Siyu Chen, Zhuoran Yang

CoRR, 2024

Contractual Reinforcement Learning: Pulling Arms with Invisible Hands.

Jibang Wu, Siyu Chen, Mengdi Wang, Huazheng Wang, Haifeng Xu

CoRR, 2024

Implicit Regularization of Gradient Flow on One-Layer Softmax Attention.

Heejune Sheen, Siyu Chen, Tianhao Wang, Harrison H. Zhou

CoRR, 2024

Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality.

Siyu Chen, Heejune Sheen, Tianhao Wang, Zhuoran Yang

CoRR, 2024

Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers.

Siyu Chen, Heejune Sheen, Tianhao Wang, Zhuoran Yang

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems.

Jianliang He, Siyu Chen, Fengzhuo Zhang, Zhuoran Yang

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality (extended abstract).

Siyu Chen, Heejune Sheen, Tianhao Wang, Zhuoran Yang

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023

Actions Speak What You Want: Provably Sample-Efficient Reinforcement Learning of the Quantal Stackelberg Equilibrium from Strategic Feedbacks.

Siyu Chen, Mengdi Wang, Zhuoran Yang

CoRR, 2023

A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations.

Siyu Chen, Yitan Wang, Zhaoran Wang, Zhuoran Yang

CoRR, 2023

Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model.

Siyu Chen, Jibang Wu, Yifan Wu, Zhuoran Yang

Proceedings of the International Conference on Machine Learning, 2023

2022

Adaptive Model Design for Markov Decision Process.

Siyu Chen, Donglin Yang, Jiayang Li, Senmiao Wang, Zhuoran Yang, Zhaoran Wang

Proceedings of the International Conference on Machine Learning, 2022

2021

Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic.

Yufeng Zhang, Siyu Chen, Zhuoran Yang, Michael I. Jordan, Zhaoran Wang

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021