כתבה
arXiv cs.LG ·
LoRA-RC: חישוב רכזי עם תיקון דרגה נמוכה
LoRA-RC: Reservoir Computing with Low-Rank Adaptation
LoRA-RC מציע תיקון דרגה נמוכה לחישוב רכזי, המקטין את השגיאה ב-56% לעומת חישוב רכזי קבוע.
תקציר מקורי באנגליתarXiv:2609.12327v1 Announce Type: cross Abstract: Reservoir computing (RC) trains only a linear readout over a fixed recurrent layer, making it fast and data-efficient for online prediction. However, a static reservoir degrades under system drift, readout-only adaptation is then insufficient, and unconstrained reservoir adaptation can destroy the echo-state and incremental stability properties that make RC reliable. This paper proposes LoRA-RC, which adapts the recurrent matrix through a low-rank correction driven by streaming prediction errors. The base reservoir and adaptation bases are fixed offline; a small core matrix is adapted online, projected onto a spectral-norm ball, and low-pass filtered at each step. The projection guarantees that every applied recurrent matrix remains within
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית