Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning
This addresses the environmental impact of privacy-preserving ML for researchers and practitioners, but it is incremental as it applies existing methods to a new aspect.
The paper investigates how differential privacy affects the carbon footprint of machine learning algorithms due to increased run-times or failed experiments, providing guidance on noise levels to balance privacy and emissions.
In recent years, machine learning techniques utilizing large-scale datasets have achieved remarkable performance. Differential privacy, by means of adding noise, provides strong privacy guarantees for such learning algorithms. The cost of differential privacy is often a reduced model accuracy and a lowered convergence speed. This paper investigates the impact of differential privacy on learning algorithms in terms of their carbon footprint due to either longer run-times or failed experiments. Through extensive experiments, further guidance is provided on choosing the noise levels which can strike a balance between desired privacy levels and reduced carbon emissions.