Bochen Lyu

According to our database, Bochen Lyu authored at least 8 papers between 2023 and 2025.

Collaborative distances:

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

2025

Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently.

Bochen Lyu, Yiyang Jia, Xiaohao Cai, Zhanxing Zhu

CoRR, November, 2025

Analyzing the Implicit Bias of Adversarial Training From a Generalized Margin Perspective.

Bochen Lyu, Zhanxing Zhu

IEEE Trans. Pattern Anal. Mach. Intell., September, 2025

Heavy-Ball Momentum Method in Continuous Time and Discretization Error Analysis.

Bochen Lyu, Xiaojing Zhang, Fangyi Zheng, He Wang, Zheng Wang, Zhanxing Zhu

CoRR, June, 2025

A Solvable Attention for Neural Scaling Laws.

Bochen Lyu, Di Wang, Zhanxing Zhu

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

DyCAST: Learning Dynamic Causal Structure from Time Series.

Yue Cheng, Bochen Lyu, Weiwei Xing, Zhanxing Zhu

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Can Language Models Serve as Analogy Annotators?

Xiaojing Zhang, Bochen Lyu

Proceedings of the Findings of the Association for Computational Linguistics, 2025

Effects of Momentum in Implicit Bias of Gradient Flow for Diagonal Linear Networks.

Bochen Lyu, He Wang, Zheng Wang, Zhanxing Zhu

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2023

Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network.

Bochen Lyu, Zhanxing Zhu

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023