Sparsity-Preserving Differentially Private Training of Large Embedding Models Badih Ghazi Google Research Mountain View, CA

Feb-8-2026, 23:58:27 GMT–Neural Information Processing Systems

We demonstrate the effectiveness of our algorithms on four benchmark datasets for online advertising and natural language understanding.

artificial intelligence, machine learning, natural language, (18 more...)

Neural Information Processing Systems

Feb-8-2026, 23:58:27 GMT

Conferences PDF

Country:
- North America > United States
  - New Jersey > Mercer County
    - Princeton (0.04)
  - California > Santa Clara County
    - Mountain View (0.40)
- Europe > Romania
  - Sud - Muntenia Development Region > Giurgiu County > Giurgiu (0.04)

Genre:
- Research Report > New Finding (0.46)

Industry:
- Information Technology
  - Security & Privacy (1.00)
  - Services (0.66)

Technology:
- Information Technology > Artificial Intelligence
  - Representation & Reasoning (1.00)
  - Natural Language (1.00)
  - Machine Learning
    - Neural Networks (0.94)
    - Statistical Learning (0.68)

Duplicate Docs Excel Report

Title
Sparsity-Preserving Differentially Private Training of Large Embedding Models

Similar Docs Excel Report more

Title	Similarity	Source
None found