Search Results for author:
Found 2 papers, 0 papers with code
RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
In this context, implementing machine learning (ML) models with real-valued weight parameters can prove to be impractical particularly for large models, and there is a need to train models with quantized discrete weights.
Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and Filtering
In particular, for fully connected layers, we combine a block-circulant based spatial restructuring with Spectral-DP to achieve better utility.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
