The Differentially Private Lottery Ticket Mechanism
This addresses privacy concerns in machine learning for applications requiring data protection, but it appears incremental as it builds on the lottery ticket hypothesis.
The paper tackles the privacy-utility trade-off in differentially private training by proposing the differentially private lottery ticket mechanism (DPLTM), which uses high-quality winners to achieve faster convergence and reduced privacy budget consumption, with transferability across datasets, domains, and architectures.
We propose the differentially private lottery ticket mechanism (DPLTM). An end-to-end differentially private training paradigm based on the lottery ticket hypothesis. Using "high-quality winners", selected via our custom score function, DPLTM significantly improves the privacy-utility trade-off over the state-of-the-art. We show that DPLTM converges faster, allowing for early stopping with reduced privacy budget consumption. We further show that the tickets from DPLTM are transferable across datasets, domains, and architectures. Our extensive evaluation on several public datasets provides evidence to our claims.