Nidham Gazagnadou

Nidham Gazagnadou

Research Scientist

Biography

I am a research scientist at Sony AI in the Privacy-Preserving Machine Learning team. Check our our blog posts to better understand our activities. Before that, I was a PhD student at Télécom Paris, supervised by Robert M. Gower.

I try to code efficient and reproducible experiments through tested open source codes. I developped the Python open source package RidgeSketch (with FAIR New York). I also contributed to the Julia suite StochOpt and briefly to BenchOpt.

I recently got interested by Quantization-Aware Training (QAT) in the Federated Learning context from both a theoretical in empirical point of view. Feel free to reach out if you want to collaborate!

Interests
  • Federated Learning
  • Stochastic Optimization
  • Edge AI
  • Computer Vision privacy
  • Vision Foundation Models
Education
  • PhD in Applied Mathematics, 2021

    Télécom Paris

  • Msc in Computer Vision and Machine Learning, 2018

    ENS Paris-Saclay

  • Engineering diploma in Applied Mathematics, 2018

    ENSTA Paris