Get started
Author

Dingzhi Yu

Observed name: Yu, Dingzhi
OpenAlex ID: A5109689425
Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise
2026 · Yu, Dingzhi, Tao, Hongyi, et al. · arXiv (Cornell University) · 16
PDF
Mirror Descent Under Generalized Smoothness
2025 · Yu, Dingzhi, Jiang, Wei, et al. · arXiv (Cornell University) · 12
PDF
Better Convergence Guarantees for Sign-Based Momentum Methods
2025 · Jiang, Wei, Yu, Dingzhi, et al. · arXiv (Cornell University) · 11
PDF
StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models
2026 · Yu, Dingzhi, Pan, Rui, et al. · arXiv (Cornell University) · 6
PDF
Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond
2024 · Yu, Dingzhi, Cai, Yunuo, et al. · arXiv (Cornell University) · 4
PDF
Open Problem: Is AdamW Effective Under Heavy-Tailed Noise?
2026 · Yu, Dingzhi, Tao, Hongyi, et al. · arXiv (Cornell University) · 3
PDF
Group Distributionally Robust Optimization with Flexible Sample Queries
2025 · Bai, Haomin, Yu, Dingzhi, et al. · arXiv (Cornell University) · 3
PDF
When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds
2026 · Tao, Hongyi, Yu, Dingzhi, et al. · arXiv (Cornell University) · 2
PDF
Improved Approximate Regret for Decentralized Online Continuous Submodular Maximization via Reductions
2026 · Wan, Yuanyu, Shen, Yu, et al. · arXiv (Cornell University) · 1
PDF
Variance Reduction with Delayed Feedback for Non-Convex Optimization
2026 · Jiang, Wei, Yu, Dingzhi, et al. · arXiv (Cornell University)
PDF
Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon
2026 · Yang, Sifan, Tao, Hongyi, et al. · arXiv (Cornell University)
PDF
Works count: 11
Citation count: 58
H-index: 4
I10-index: 3
Year
Topic
Type