Alcove
发表于 2025-4-1 03:02:14
http://reply.papertrans.cn/67/6632/663145/663145_61.png
Oligarchy
发表于 2025-4-1 08:12:54
http://reply.papertrans.cn/67/6632/663145/663145_62.png
诱骗
发表于 2025-4-1 10:40:02
Robust Distributed Training of Linear Classifiers Based on Divergence Minimization Principle/loss bound analysis indicates the advantage of our Beta-IPM in contaminated environments. Experiments with various datasets revealed that, even when 80% of the shards are contaminated, Beta-IPM can suppress the influence of the contamination.