Yulian Wu
7 papers · 2022–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
π
Conference Polyglot Β· Silver
π
Interdisciplinary Bridge Β· Silver
πΊοΈ
Taxonomy Completionist
(19)
π
Keyword Champion
(2)
π
Renaissance Researcher
(5)
Top co-authors
Research topics
Machine Learning
(7)
Optimization & Theory
(7)
Application Areas
(4)
Artificial Intelligence
(3)
Security & Privacy
(3)
Differential Privacy
(3)
Learning Types
(3)
Mathematics & Optimization
(2)
Reinforcement Learning
(2)
Core AI
(2)
Methods
(2)
Optimization
(2)
Natural Language Processing
(1)
Bayesian & Probabilistic Β· Machine Learning
(1)
Bayesian & Probabilistic Β· Artificial Intelligence
(1)
Keywords
heavy-tailed reward
(3)
differential privacy
(3)
regret bound
(3)
offline alignment
(2)
multi-armed bandit
(2)
sparse learning
(1)
kl divergence
(1)
preference optimization
(1)
markov decision process
(1)
posterior distribution
(1)
value iteration
(1)
kullback-leibler divergence
(1)
generalization error
(1)
concentration inequalities
(1)
robust estimation
(1)
ucb algorithm
(1)
concentration inequality
(1)
upper confidence bound
(1)
pac-bayes bound
(1)
adversarial corruption
(1)
Papers
A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
ICML 2025
Square$Ο$PO: Differentially Private and Robust $Ο^2$-Preference Optimization in Offline Direct Alignment
ICML 2025
Better-than-KL PAC-Bayes Bounds
COLT 2024
Differentially Private Episodic Reinforcement Learning with Heavy-tailed Rewards
ICML 2023
On Private and Robust Bandits
NeurIPS 2023
Optimal Rates of (Locally) Differentially Private Heavy-tailed Multi-Armed Bandits
AISTATS 2022
Private Stochastic Convex Optimization and Sparse Learning with Heavy-tailed Data Revisited
IJCAI 2022