Differential Privacy of Gradient Descent on Perturbed Objectives
Proves explicit privacy bounds for finite gradient-descent iterates on perturbed objectives, removing ambient-dimension factors for generalized linear models.
1 stories, newest first · one card per story
Proves explicit privacy bounds for finite gradient-descent iterates on perturbed objectives, removing ambient-dimension factors for generalized linear models.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views