Picture for Daogao Liu

Daogao Liu

MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Add code
Jul 08, 2024
Viaarxiv icon

Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning

Add code
Jun 20, 2024
Viaarxiv icon

Private Online Learning via Lazy Algorithms

Add code
Jun 05, 2024
Viaarxiv icon

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation

Add code
Feb 21, 2024
Viaarxiv icon

User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates

Add code
Nov 07, 2023
Figure 1 for User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates
Viaarxiv icon

Detecting Pretraining Data from Large Language Models

Add code
Nov 03, 2023
Figure 1 for Detecting Pretraining Data from Large Language Models
Figure 2 for Detecting Pretraining Data from Large Language Models
Figure 3 for Detecting Pretraining Data from Large Language Models
Figure 4 for Detecting Pretraining Data from Large Language Models
Viaarxiv icon

Learning across Data Owners with Joint Differential Privacy

Add code
May 25, 2023
Figure 1 for Learning across Data Owners with Joint Differential Privacy
Figure 2 for Learning across Data Owners with Joint Differential Privacy
Figure 3 for Learning across Data Owners with Joint Differential Privacy
Figure 4 for Learning across Data Owners with Joint Differential Privacy
Viaarxiv icon

Algorithmic Aspects of the Log-Laplace Transform and a Non-Euclidean Proximal Sampler

Add code
Feb 22, 2023
Viaarxiv icon

$k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models

Add code
Feb 21, 2023
Figure 1 for $k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models
Figure 2 for $k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models
Figure 3 for $k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models
Figure 4 for $k$NN-Adapter: Efficient Domain Adaptation for Black-Box Language Models
Viaarxiv icon

Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks

Add code
Feb 20, 2023
Figure 1 for Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
Figure 2 for Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
Figure 3 for Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks
Viaarxiv icon