Entropy and Private Language Models

Abstract

We presented our research on entropy and private language models, exploring novel approaches to maintaining privacy while preserving model performance.

Date
Apr 1, 2025 2:00 PM — 3:00 PM
Event
NYU CILVR Seminar
Location
New York University
New York, NY
Click on the Slides button above to view the built-in slides feature.

Slides can be added in a few ways:

  • Create slides using Wowchemy’s Slides feature and link using slides parameter in the front matter of the talk file
  • Upload an existing slide deck to static/ and link using url_slides parameter in the front matter of the talk file
  • Embed your slides (e.g. Google Slides) or presentation video on this page using shortcodes.

Further event details, including page elements such as image galleries, can be added to the body of this page.

Nandan Kumar Jha
Nandan Kumar Jha
PhD student at NYU CCS

The broader goal is to guide LLM design from first principles, enabling more efficient pre-training, faster (private) inference, and robust generalization.

Related