ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.
month = apr, year =
3 Pith papers cite this work, alongside 97 external citations. Polarity classification is still indexing.
3
Pith papers citing it
97
external citations · external index
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Sampler-Robust Optimization finds decisions stable under perturbations of generative samplers and supplies high-probability upper bounds on the true objective under a coverage assumption.
EDRBO uses ensemble surrogates and Wasserstein ambiguity sets to robustify BO acquisition functions against context distribution mismatch, with sublinear regret O(γ_T √T) and SOTA empirical results on continuous contexts.
citing papers explorer
-
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.
-
Sampler-Robust Optimization under Generative Models
Sampler-Robust Optimization finds decisions stable under perturbations of generative samplers and supplies high-probability upper bounds on the true objective under a coverage assumption.
-
Ensemble Distributionally Robust Bayesian Optimisation with Continuous Context
EDRBO uses ensemble surrogates and Wasserstein ambiguity sets to robustify BO acquisition functions against context distribution mismatch, with sublinear regret O(γ_T √T) and SOTA empirical results on continuous contexts.