Wanyun Xie
5 papers · 2023–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🐝
Cross-Pollinator
(15)
Conferences
ICML (3)
NIPS (2)
Top co-authors
Keywords
stochastic gradient descent
(1)
neural network training
(1)
nonconvex optimization
(1)
sharpness-aware minimization
(1)
neural network optimization
(1)
loss landscape
(1)
parallel computing
(1)
gradient computation
(1)
convergence guarantee
(1)
generative adversarial network
(1)
model generalization
(1)
lookahead optimizer
(1)
gradient descent ascent
(1)
parallel training
(1)
linear interpolation
(1)
Papers
Training Deep Learning Models with Norm-Constrained LMOs
ICML 2025
Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning
ICML 2025
SAMPa: Sharpness-aware Minimization Parallelized
NIPS 2024
Improving SAM Requires Rethinking its Optimization Formulation
ICML 2024
Stable Nonconvex-Nonconcave Training via Linear Interpolation
NIPS 2023