Metraipolis › archive › dc_c44da5d54dc7
Adaptive Forgetting for Nonstationary Optimization: Towards Robust EEG Decoding — arXiv:2609.24233
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24233
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T07:04:09.127Z
- SHA-256 of the archived text
fb9d1d20bfcc8d49f0bcf01a1a0b2724ef24ecea7dd3f7d048c461307c96745f- Stable URL of this page
https://metraipolis.com/documento/dc_c44da5d54dc7
How to cite
Adaptive Forgetting for Nonstationary Optimization: Towards Robust EEG Decoding — arXiv:2609.24233 — arXiv (en), https://arxiv.org/abs/2609.24233 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c44da5d54dc7 (Metraipolis archive dc_c44da5d54dc7, sha256 fb9d1d20bfcc8d49f0bcf01a1a0b2724ef24ecea7dd3f7d048c461307c96745f)
BibTeX
@misc{dcc44da5d54dc7,
title = {Adaptive Forgetting for Nonstationary Optimization: Towards Robust EEG Decoding — arXiv:2609.24233},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24233},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c44da5d54dc7; sha256 fb9d1d20bfcc8d49f0bcf01a1a0b2724ef24ecea7dd3f7d048c461307c96745f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24233. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Electroencephalography (EEG) provides non-invasive monitoring of brain activity and is widely used in emotion recognition, motor imagery and sleep staging. Although within-subject decoding has achieved considerable progress, cross-subject generalization remains a central challenge in practical applications. EEG decoders are typically trained with Adam/AdamW under a fixed second-moment decay coefficient, even though cross-subject learning involves low signal-to-noise ratios, subject variability, and gradient nonstationarity. A fixed coefficient implicitly assumes that gradient statistics are homogeneous across layers and time, which can limit model's adaptability to cross-subject EEG signals and degrade generalization. To address these issues, we propose AFOR, a tensor-wise adaptive optimizer that converts the fixed second-moment decay coefficient into a dynamic coefficient estimated online from local gradient state. AFOR combines a Residual-Alignment Signal Scorer (RASS) and an Adaptive Forgetting Controller (AFC). RASS summarizes local gradient residuals and directional agreement into a signal-quality score, and AFC maps this score through self-referential normalization to a bounded per-step decay coefficient, with cumulative-product initialization correction maintaining consistency under time-varying decay. Under a strict cross-subject protocol on three EEG benchmarks that cover three representative fields, AFOR achieves the best average performance among the compared optimizers, improving the mean test accuracy over Adam by 3.00%, 2.07%, and 4.38%, respectively. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.HC). Categorie arXiv: Machine Learning (cs.LG) ; Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2609.24233 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:56:29.264Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).