6 papers
Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning
Tieliang Gong, Zhongbo Zhang, Wen Wen +1
Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies…
Beyond Sharpness: A Flatness Decomposition Framework for Efficient Continual Learning
Yanan Chen, Tieliang Gong, Yunjiao Zhang +1
Continual Learning (CL) aims to enable models to sequentially learn multiple tasks without forgetting previous knowledge. Recent studies have shown that optimizing towards flatter…
Information-Theoretic Generalization Bounds of Replay-based Continual Learning
Wen Wen, Tieliang Gong, Zeyu Gao +3
Continual learning (CL) has emerged as a dominant paradigm for acquiring knowledge from sequential tasks while avoiding catastrophic forgetting. Although many CL methods have been…
A Unified Information-Theoretic Framework for Meta-Learning Generalization
Wen Wen, Tieliang Gong, Yuxin Dong +2
In recent years, information-theoretic generalization bounds have gained increasing attention for analyzing the generalization capabilities of meta-learning algorithms. However, ex…
InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective
Yuanhong Zhang, Muyao Yuan, Weizhan Zhang +4
The Segment Anything Model (SAM), a vision foundation model, exhibits impressive zero-shot capabilities in general tasks but struggles in specialized domains. Parameter-efficient f…
Towards the Generalization of Multi-view Learning: An Information-theoretical Analysis
Wen Wen, Tieliang Gong, Yuxin Dong +2
Multiview learning has drawn widespread attention for its efficacy in leveraging cross-view consensus and complementarity information to achieve a comprehensive representation of d…