Daogao Liu
17 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Renaissance Researcher (5) π Conference Polyglot (5) π Interdisciplinary Bridge π Cross-Pollinator (11) πΊοΈ Taxonomy Completionist (13)
πΊοΈ
Taxonomy Completionist
(13)
π§
Keyword Pioneer
π
Triple Crown
π
Keyword Champion
(2)
β‘
Prolific Year
(6)
π₯
Unstoppable
(5)
π
Century Club
(17)
β
The Questioner
Conferences
NIPS (6)
ICLR (5)
COLT (3)
ICML (2)
AISTATS (1)
Top co-authors
Research topics
Keywords
differential privacy
(9)
stochastic convex optimization
(4)
gradient descent
(3)
user-level privacy
(2)
exponential mechanism
(2)
privacy-preserving learning
(1)
distributed learning
(1)
non-convex optimization
(1)
empirical risk minimization
(1)
graph clustering
(1)
variance reduction
(1)
online convex optimization
(1)
excess risk
(1)
outlier removal
(1)
high-dimensional optimization
(1)
markov chain monte carlo
(1)
excess risk bound
(1)
correlation clustering
(1)
empirical risk
(1)
gradient estimation
(1)
Papers
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
ICLR 2025
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
ICLR 2025
Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
ICML 2025
Adaptive Batch Size for Privately Finding Second-Order Stationary Points
ICLR 2025
Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
NIPS 2024
Private Online Learning via Lazy Algorithms
NIPS 2024
User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates
AISTATS 2024
Detecting Pretraining Data from Large Language Models
ICLR 2024
Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
ICML 2024
Faster Algorithms for User-Level Private Stochastic Convex Optimization
NIPS 2024
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
NIPS 2023
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
ICLR 2023
Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler
COLT 2023
Better Private Algorithms for Correlation Clustering
COLT 2022
When Does Differentially Private Learning Not Suffer in High Dimensions?
NIPS 2022
Private Convex Optimization via Exponential Mechanism
COLT 2022
Private Non-smooth ERM and SCO in Subquadratic Steps
NIPS 2021