Setting β in balanced Adam to achieve a refresh count R_β ≈1000 based on effective learning horizon T_ES improves validation robustness over fixed-β baselines across 11 vision and language experiments.
7 Fern´andez-Hern´andez P´erez-Corral Mestre Dolz Duato Quintana-Ort´ı Ya Le and Xuan Yang
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Refresh-Scaling the Memory of Balanced Adam
Setting β in balanced Adam to achieve a refresh count R_β ≈1000 based on effective learning horizon T_ES improves validation robustness over fixed-β baselines across 11 vision and language experiments.