Andrew Lowy

collaborators

2 papers

cs.LG2026

Near-Optimal Pure Machine Unlearning for Smooth Strongly Convex Losses

Matthew Regehr, Gautam Kamath, Andrew Lowy

Machine unlearning is motivated by legal and user-facing requirements to remove the influence of individuals' data from trained models, such as the right to be forgotten. Prior wor…

cs.LG2026

Optimal Rates for Pure $ε$ -Differentially Private Stochastic Convex Optimization with Heavy Tails

Andrew Lowy

We study stochastic convex optimization (SCO) with heavy-tailed gradients under pure $ε$ -differential privacy (DP). Instead of assuming a bound on the worst-case Lipschit…

Near-Optimal Pure Machine Unlearning for Smooth Strongly Convex Losses

Optimal Rates for Pure ε-Differentially Private Stochastic Convex Optimization with Heavy Tails

Optimal Rates for Pure $ε$ -Differentially Private Stochastic Convex Optimization with Heavy Tails