ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.
and Mitter, Sanjoy K
3 Pith papers cite this work, alongside 213 external citations. Polarity classification is still indexing.
3
Pith papers citing it
213
external citations · OpenAlex
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
General criteria extend L^p-mean Wasserstein convergence rates of occupation measures to non-stationary or non-Markovian ergodic processes under conditional convergence to equilibrium, with applications to Brownian diffusions and fractional Brownian driven SDEs.
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.
-
Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
Recasts sampling-based nonconvex optimization as smoothed gradient descent to obtain non-asymptotic convergence guarantees and introduces the DIDA annealed algorithm that converges to the global optimum.
-
Convergence rate of the occupation measure of classes of ergodic processes toward their invariant distribution in mean Wasserstein distance
General criteria extend L^p-mean Wasserstein convergence rates of occupation measures to non-stationary or non-Markovian ergodic processes under conditional convergence to equilibrium, with applications to Brownian diffusions and fractional Brownian driven SDEs.