Picture for Pasin Manurangsi

Pasin Manurangsi

On Convex Optimization with Semi-Sensitive Features

Add code
Jun 27, 2024
Viaarxiv icon

Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models

Add code
Jun 23, 2024
Viaarxiv icon

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

Add code
Jun 20, 2024
Viaarxiv icon

Differentially Private Optimization with Sparse Gradients

Add code
Apr 16, 2024
Viaarxiv icon

How Private is DP-SGD?

Add code
Mar 26, 2024
Figure 1 for How Private is DP-SGD?
Figure 2 for How Private is DP-SGD?
Figure 3 for How Private is DP-SGD?
Figure 4 for How Private is DP-SGD?
Viaarxiv icon

Training Differentially Private Ad Prediction Models with Semi-Sensitive Features

Add code
Jan 26, 2024
Viaarxiv icon

Optimal Unbiased Randomizers for Regression with Label Differential Privacy

Add code
Dec 09, 2023
Viaarxiv icon

Sparsity-Preserving Differentially Private Training of Large Embedding Models

Add code
Nov 14, 2023
Figure 1 for Sparsity-Preserving Differentially Private Training of Large Embedding Models
Figure 2 for Sparsity-Preserving Differentially Private Training of Large Embedding Models
Figure 3 for Sparsity-Preserving Differentially Private Training of Large Embedding Models
Figure 4 for Sparsity-Preserving Differentially Private Training of Large Embedding Models
Viaarxiv icon

User-Level Differential Privacy With Few Examples Per User

Add code
Sep 21, 2023
Figure 1 for User-Level Differential Privacy With Few Examples Per User
Figure 2 for User-Level Differential Privacy With Few Examples Per User
Viaarxiv icon

A Note on Hardness of Computing Recursive Teaching Dimension

Add code
Jul 19, 2023
Viaarxiv icon