7 citations · 12 across the 10 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Forking: Sudden Overfitting Under Replay
Shanbin Yu, Shaoyang Guo, Haoran Zhao +2
This paper studies forking, a generalization failure discovered in NanoGPT autoresearch. Under data replay, models with an over-encoding n-gram memory branch show a sharp separatio…
cs.LG2022★ 1 cited
Anchor Sampling for Federated Learning with Partial Client Participation
Feijie Wu, Song Guo, Zhihao Qu +3
Compared with full client participation, partial client participation is a more practical scenario in federated learning, but it may amplify some challenges in federated learning,…