4 citations · 15 across the 10 of their papers we have counts for
10 papers
SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution
Yuze Wang, Yujia Tong, Xuan Liu +1
Large Language Models (LLMs) inevitably memorize sensitive information during training, posing significant privacy risks. Machine unlearning has emerged as a promising solution to…
Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation
Yaohua Liu, Jiaxin Gao, Xuan Liu +3
Transfer attacks generate significant interest for real-world black-box applications by crafting transferable adversarial examples through surrogate models. Whereas, existing works…
Learning with Constraint Learning: New Perspective, Solution Strategy and Various Applications
Risheng Liu, Jiaxin Gao, Xuan Liu +1
The complexity of learning problems, such as Generative Adversarial Network (GAN) and its variants, multi-task and meta-learning, hyper-parameter learning, and a variety of real-wo…
Hierarchical Optimization-Derived Learning
Risheng Liu, Xuan Liu, Shangzhi Zeng +2
In recent years, by utilizing optimization techniques to formulate the propagation of deep model, a variety of so-called Optimization-Derived Learning (ODL) approaches have been pr…
Optimization-Derived Learning with Essential Convergence Analysis of Training and Hyper-training
Risheng Liu, Xuan Liu, Shangzhi Zeng +2
Recently, Optimization-Derived Learning (ODL) has attracted attention from learning and vision areas, which designs learning models from the perspective of optimization. However, p…
Revisiting GANs by Best-Response Constraint: Perspective, Methodology, and Application
Risheng Liu, Jiaxin Gao, Xuan Liu +1
In past years, the minimax type single-level optimization formulation and its variations have been widely utilized to address Generative Adversarial Networks (GANs). Unfortunately,…
Towards Extremely Fast Bilevel Optimization with Self-governed Convergence Guarantees
Risheng Liu, Xuan Liu, Wei Yao +2
Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning and vision fields. The validity of existing works heavily relies on solving a series…
Value-Function-based Sequential Minimization for Bi-level Optimization
Risheng Liu, Xuan Liu, Shangzhi Zeng +2
Gradient-based Bi-Level Optimization (BLO) methods have been widely applied to handle modern learning tasks. However, most existing strategies are theoretically designed based on r…
A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization
Risheng Liu, Xuan Liu, Xiaoming Yuan +2
Bi-level optimization model is able to capture a wide range of complex learning tasks with practical interest. Due to the witnessed efficiency in solving bi-level programs, gradien…
Defending Against Adversarial Attacks in Transmission- and Distribution-level PMU Data
Jun Jiang, Xuan Liu, Scott Wallace +3
Phasor measurement units (PMUs) provide high-fidelity data that improve situation awareness of electric power grid operations. PMU datastreams inform wide-area state estimation, mo…