4 papers
Predictability as a Fine-Grained Measure for Privacy
Linda Lu, Karthik Sridharan
Differential privacy (DP) ensures rigorous individual-level privacy guarantees against even the most knowledgeable attackers, but its worst-case nature can impose a costly privacy-…
On the Robustness of Langevin Dynamics to Score Function Error
Daniel Yiming Cao, August Y. Chen, Karthik Sridharan +1
We consider the robustness of score-based generative modeling to errors in the estimate of the score function. In particular, we show that Langevin dynamics is not robust to the $L…
System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
Linda Lu, Ayush Sekhari, Karthik Sridharan
Machine unlearning addresses the problem of updating a machine learning model/system trained on a dataset so that the influence of a set of deletion requests on…
Active Learning via Regression Beyond Realizability
Atul Ganju, Shashaank Aiyer, Ved Sriraman +1
We present a new active learning framework for multiclass classification based on surrogate risk minimization that operates beyond the standard realizability assumption. Existing s…