High-probability generalization bounds for D-SGD are derived at the optimal rate O(1/sqrt(mn) log(1/δ)) via pointwise uniform stability across convex and non-convex settings.
International Conference on Machine Learning , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
For binary classification in the NTK regime, LoRA rank r=1 suffices and is often optimal under cross-entropy loss, reducing the prior sufficient condition from r>=12.
citing papers explorer
-
Unveiling High-Probability Generalization in Decentralized SGD
High-probability generalization bounds for D-SGD are derived at the optimal rate O(1/sqrt(mn) log(1/δ)) via pointwise uniform stability across convex and non-convex settings.
-
Rethinking the Rank Threshold for LoRA Fine-Tuning
For binary classification in the NTK regime, LoRA rank r=1 suffices and is often optimal under cross-entropy loss, reducing the prior sufficient condition from r>=12.