Scholar
Yulian Wu
Google Scholar ID: 10E7OtIAAAAJ
King Abdullah University of Science and Technology
Citations & Impact
Citations
146
H-index
7
i10-index
4
Publications
12
Co-authors
5
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published 'Optimal Regret of Bernoulli Bandits under Global Differential Privacy' at NeurIPS 2025
- Published two papers at ICML 2025: 'A Unified Theoretical Analysis of Private and Robust Offline Alignment' (Spotlight, acceptance rate 2.6%) and 'Square𝜒PO: Differentially Private and Robust 𝜒2-Preference Optimization'
- Published 'Better-than-KL PAC-Bayes Bounds' at COLT 2024
- Co-first authored 'PPML-Omics: a Privacy-Preserving federated Machine Learning system protects patients’ privacy from omic data' in Science Advances (Impact Factor = 15.4, 2024)
- Co-first authored 'On Private and Robust Bandits' at NeurIPS 2023
- Published 'Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards' at ICML 2023
- Published 'Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits' at AISTATS 2022 (Oral presentation, acceptance rate 2.6%)
- Published 'Private Stochastic Convex Optimization and Sparse Learning with Heavy-tailed Data Revisited' at IJCAI 2022
- Master’s thesis: 'Performance Improvement Based on Pinball Support Vector Machine' (2021)
- Multiple preprints on differentially private RLHF, quantum heavy-tailed bandits, and quantum-enhanced reinforcement learning
