DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling

arXiv:2509.03472v2 Announce Type: replace-cross Abstract: Differentially-Private SGD (DP-SGD) and its adaptive variant DP-Adam are powerful techniques to protect user privacy when using sensitive data to train neural networks. During training, converting model weights and activations into low-precision formats, i.e., quantization, can drastically reduce training times, energy consumption, and cost, and is thus a widely used technique. In this work, we demonstrate for the first time that quantiza