Wanyun Xie

According to our database, Wanyun Xie authored at least 8 papers between 2017 and 2025.

Collaborative distances:

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

2025

Generalized Gradient Norm Clipping & Non-Euclidean (L₀,L₁)-Smoothness.

Thomas Pethick, Wanyun Xie, Mete Erdogan, Kimon Antonakopoulos, Tony Silveti-Falls, Volkan Cevher

CoRR, June, 2025

Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning.

Wanyun Xie, Francesco Tonin, Volkan Cevher

CoRR, May, 2025

Training Deep Learning Models with Norm-Constrained LMOs.

Thomas Pethick, Wanyun Xie, Kimon Antonakopoulos, Zhenyu Zhu, Antonio Silveti-Falls, Volkan Cevher

CoRR, February, 2025

2024

Mixed Nash for Robust Federated Learning.

Wanyun Xie, Thomas Pethick, Ali Ramezani-Kebrya, Volkan Cevher

Trans. Mach. Learn. Res., 2024

SAMPa: Sharpness-aware Minimization Parallelized.

Wanyun Xie, Thomas Pethick, Volkan Cevher

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

Improving SAM Requires Rethinking its Optimization Formulation.

Wanyun Xie, Fabian Latorre, Kimon Antonakopoulos, Thomas Pethick, Volkan Cevher

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

2023

Stable Nonconvex-Nonconcave Training via Linear Interpolation.

Thomas Pethick, Wanyun Xie, Volkan Cevher

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

2017

Nonlinear Dimensionality Reduction via Homeomorphic Tangent Space and Compactness.

Shaoqun Zhang, Wanyun Xie

Proceedings of the Data Science, 2017