Scholar
Yuan Cao
Google Scholar ID: -VGnHI4AAAAJ
The University of Hong Kong
Machine Learning
Optimization
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
3,209
H-index
19
i10-index
28
Publications
20
Co-authors
0
Contact
Email
yuancao@hku.hk
Twitter
Open ↗
GitHub
Open ↗
Publications
1 items
Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
2026
Cited
0
Resume (English only)
Academic Achievements
Multiple papers accepted at NeurIPS 2024, including 'The Implicit Bias of Adam on Separable Data', 'Attention Boosted Individualized Regression', etc.
Paper accepted at ICML 2024: 'Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data'
Published at COLT 2023: 'The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks'
Published at ICML 2023: 'The Benefits of Mixup for Feature Learning'
Publications in top journals including JMLR, TMLR, and MLJ
Several preprints on arXiv, e.g., 'Estimation of Out-of-Sample Sharpe Ratio for High Dimensional Portfolio Optimization'
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up