4 papers
Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery
Shiji Zhou, Tianbai Yu, Zhi Zhang +4
Machine unlearning (MU) aims to efficiently remove sensitive or harmful memory from a pre-trained model. The key challenge is to balance the potential tradeoff between unlearning e…
Moment Alignment: Unifying Gradient and Hessian Matching for Domain Generalization
Yuen Chen, Haozhe Si, Guojun Zhang +1
Domain generalization (DG) seeks to develop models that generalize well to unseen target domains, addressing the prevalent issue of distribution shifts in real-world applications.…
MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning
Jingyan Shen, Jiarui Yao, Rui Yang +5
Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, rew…
Towards Understanding the Role of Sharpness-Aware Minimization Algorithms for Out-of-Distribution Generalization
Samuel Schapiro, Han Zhao
Recently, sharpness-aware minimization (SAM) has emerged as a promising method to improve generalization by minimizing sharpness, which is known to correlate well with generalizati…