Skip to yearly menu bar Skip to main content

Workshop: Workshop on Socially Responsible Machine Learning

Towards Quantifying the Carbon Emissions of Differentially Private Machine Learning

Rakshit Naidu · Harshita Diddee · Ajinkya Mulay · Vardhan Aleti · Krithika Ramesh · Ahmed Zamzam


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.

Chat is not available.