Xie, Wanyun

8 publications

ICML 2025 Chameleon: A Flexible Data-Mixing Framework for Language Model Pretraining and Finetuning Wanyun Xie, Francesco Tonin, Volkan Cevher

ICLRW 2025 Chameleon: A Flexible Data-Mixing Framework for Language Model Pretraining and Finetuning Wanyun Xie, Francesco Tonin, Volkan Cevher

NeurIPS 2025 Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness Thomas Pethick, Wanyun Xie, Mete Erdogan, Kimon Antonakopoulos, Tony Silveti-Falls, Volkan Cevher

ICML 2025 Training Deep Learning Models with Norm-Constrained LMOs Thomas Pethick, Wanyun Xie, Kimon Antonakopoulos, Zhenyu Zhu, Antonio Silveti-Falls, Volkan Cevher

ICML 2024 Improving SAM Requires Rethinking Its Optimization Formulation Wanyun Xie, Fabian Latorre, Kimon Antonakopoulos, Thomas Pethick, Volkan Cevher

TMLR 2024 Mixed Nash for Robust Federated Learning Wanyun Xie, Thomas Pethick, Ali Ramezani-Kebrya, Volkan Cevher

NeurIPS 2024 SAMPa: Sharpness-Aware Minimization Parallelized Wanyun Xie, Thomas Pethick, Volkan Cevher

NeurIPS 2023 Stable Nonconvex-Nonconcave Training via Linear Interpolation Thomas Pethick, Wanyun Xie, Volkan Cevher