paper-conference

FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity (ICLR 2024)
We introduce FedP3, a flexible and privacy-aware federated network pruning framework, addressing model heterogeneity and allowing client-specific personalization.
Kai Yi, Nidham Gazagnadou, Peter Richtárik, Lingjuan Lyu
PDF Code
FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity (ICLR 2024)
Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception? (spotlight, NeurIPS 2023)
Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction …
Xiaoxiao Sun, Nidham Gazagnadou, Vivek Sharma, Lingjuan Lyu, Hongdong Li, Liang Zheng
PDF Cite Code Project Poster
Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception? (spotlight, NeurIPS 2023)
Towards closing the gap between the theory and practice of SVRG (NeurIPS 2019)
Among the very first variance reduced stochastic methods for solving the empirical risk minimization problem was the SVRG method …
Othmane Sebbouh, Nidham Gazagnadou, Samy Jelassi, Francis Bach, Robert M. Gower
PDF Cite Code
Optimal Mini-Batch and Step Sizes for SAGA (ICML 2019)
Recently it has been shown that the step sizes of a family of variance reduced gradient methods called the JacSketch methods depend on …
Nidham Gazagnadou, Robert M. Gower, Joseph Salmon
PDF Cite Code
Optimal Mini-Batch and Step Sizes for SAGA (ICML 2019)