| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Sun, 06 Oct 2024 11:04:39 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"67026ec7-50ef"
expires: Mon, 29 Dec 2025 08:17:22 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 9597:3A7A40:877D21:98491F:695236B9
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 08:07:22 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210027-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766995642.975521,VS0,VE223
vary: Accept-Encoding
x-fastly-request-id: 9c5a039e2de14deb47d6a909b7d7da7d5e7350e7
content-length: 5805
Nidham Gazagnadou
Biography
I am a research scientist in AI. Before that, I was a PhD student at Télécom Paris, supervised by Robert M. Gower, and then worked at Sony AI in the Privacy-Preserving Machine Learning team.
I try to code efficient and reproducible experiments through tested open source codes. I developed the Python open source package RidgeSketch (with FAIR New York). I also contributed to the Julia suite StochOpt and briefly to BenchOpt.
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
Papers
FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity (ICLR 2024)
Kai Yi, Nidham Gazagnadou, Peter Richtárik, Lingjuan Lyu
Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception? (spotlight, NeurIPS 2023)
Xiaoxiao Sun, Nidham Gazagnadou, Vivek Sharma, Lingjuan Lyu, Hongdong Li, Liang Zheng
On the Hardness of Robustness Transfer: A Perspective from Rademacher Complexity over Symmetric Difference Hypothesis Space (preprint)
Yuyang Deng, Nidham Gazagnadou, Junyuan Hong, Mehrdad Mahdavi, Lingjuan Lyu
RidgeSketch: A Fast Sketching Based Solver for Large Scale Ridge Regression (SIMAX 2022)
Nidham Gazagnadou, Mark Ibrahim, Robert M. Gower
Cutting some slack for SGD with adaptive Polyak stepsizes (preprint)
Robert M Gower, Mathieu Blondel, Nidham Gazagnadou, Fabian Pedregosa
Expected smoothness for stochastic variance-reduced methods and sketch-and-project methods for structured linear systems (PhD thesis)
Nidham Gazagnadou
Towards closing the gap between the theory and practice of SVRG (NeurIPS 2019)
Othmane Sebbouh, Nidham Gazagnadou, Samy Jelassi, Francis Bach, Robert M. Gower
Optimal Mini-Batch and Step Sizes for SAGA (ICML 2019)
Nidham Gazagnadou, Robert M. Gower, Joseph Salmon