conftrace_

gradient difference

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

machine unlearning (2) large language model (1) normalized gradient descent (1) influence attribution (1) multi-task optimization (1) utility bound (1) learning rate scheduler (1) model utility (1) weight attribution (1) model utility preservation (1)

Papers

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate NAACL 2025 WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models NeurIPS 2024 DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning ICML 2023