1 code implementation • 10 Feb 2022 • Timothy Stevens, Ivoline C. Ngong, David Darais, Calvin Hirsch, David Slater, Joseph P. Near
We present backpropagation clipping, a novel variant of differentially private stochastic gradient descent (DP-SGD) for privacy-preserving deep learning.
no code implementations • 9 Feb 2022 • Krystal Maughan, Ivoline C. Ngong, Joseph P. Near
As AI-based systems increasingly impact many areas of our lives, auditing these systems for fairness is an increasingly high-stakes problem.
no code implementations • 30 Nov 2020 • Ivoline C. Ngong, Krystal Maughan, Joseph P. Near
Group fairness metrics can detect when a deep learning model behaves differently for advantaged and disadvantaged groups, but even models that score well on these metrics can make blatantly unfair predictions.