Daogao Liu
18 papers · 2021–2026 · 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 ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (25) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Triple Crown
π¬
Deep Specialist
(12)
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(85)
Top co-authors
Research topics
Machine Learning
(18)
Optimization & Theory
(14)
Application Areas
(13)
Mathematics & Optimization
(8)
Optimization
(8)
Security & Privacy
(5)
Differential Privacy
(5)
Learning Types
(4)
Artificial Intelligence
(3)
Core AI
(2)
Learning Paradigms
(2)
Computer Science
(1)
Deep Learning
(1)
Natural Language Processing
(1)
Bayesian & Probabilistic
(1)
Keywords
differential privacy
(11)
stochastic convex optimization
(5)
gradient descent
(4)
machine unlearning
(2)
exponential mechanism
(2)
convex optimization
(2)
second-order stationary point
(2)
differentially private
(2)
sample complexity
(2)
user-level privacy
(2)
graph clustering
(1)
privacy-preserving learning
(1)
gradient estimation
(1)
markov chain monte carlo
(1)
stochastic gradient descent
(1)
distributed learning
(1)
excess risk
(1)
non-convex optimization
(1)
online convex optimization
(1)
variance reduction
(1)
Papers
Nearly Linear-Time User-Level DP-SCO with Optimal Rates
COLT 2026
Adaptive Batch Size for Privately Finding Second-Order Stationary Points
ICLR 2025
Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization
ICML 2025
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
ICLR 2025
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
ICLR 2025
Detecting Pretraining Data from Large Language Models
ICLR 2024
Faster Algorithms for User-Level Private Stochastic Convex Optimization
NeurIPS 2024
Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation
ICML 2024
Private Online Learning via Lazy Algorithms
NeurIPS 2024
Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
NeurIPS 2024
User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates
AISTATS 2024
Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler
COLT 2023
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
ICLR 2023
Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
NeurIPS 2023
Better Private Algorithms for Correlation Clustering
COLT 2022
Private Convex Optimization via Exponential Mechanism
COLT 2022
When Does Differentially Private Learning Not Suffer in High Dimensions?
NeurIPS 2022
Private Non-smooth ERM and SCO in Subquadratic Steps
NeurIPS 2021