Can You Fake It Until You Make It? - Impacts of Differentially Private Synthetic Data on Downstream Classification Fairness

Can You Fake It Until You Make It? - Impacts of Differentially Private Synthetic Data on Downstream Classification Fairness

Explore the impacts of differentially private synthetic data on downstream classification fairness in this 18-minute conference talk presented at the Association for Computing Machinery (ACM). Delve into the concept of "faking it until you make it" in the context of data privacy and machine learning fairness. Follow the speaker's journey through the motivation behind the research, theoretical proofs, experimental pipeline, and key findings. Gain insights into the complex relationship between privacy-preserving techniques and fairness in classification tasks, and understand the implications for developing more equitable AI systems.