arXiv cs.AI· Khizar Qureshi·· 4 小时前AI 评分24
无重放循环状态迁移的信息极限
Information Limits of Replay-Free Recurrent State Migration
AI 导读
研究刻画了循环模型被替换前必须保留的信息量:对时不变仿射线性族,order-k 局部迁移所需的最小连续因果记忆等于提升系数系统的可达维度减去锚点状态信息。可控 d 状态模型至多需 kd 个额外实坐标,单个秩一方向即可用满 kd。
正文 · 原文
Abstract:When a recurrent model is replaced, its old state may not determine what the new model would compute from the same history. We characterize the information that must be retained before the replacement is known. For a time-invariant affine linear family, the minimum continuous causal memory for order-$k$ local migration equals the reachable dimension of a lifted coefficient system minus the information in the anchor state. A controllable $d$-state model with scalar input needs at most $kd$ additional real coordinates, even when arbitrary matrix replacement directions are revealed only after streaming. A single rank-one direction can already require all $kd$. Conditional singular values and auxiliary-bit bounds distinguish this local information law from recovery at a fixed tolerance. We also give invariant-subspace and future-output constructions. Controlled experiments compare the resulting representations. In a small language model, equal-memory cubic interpolation improves mean state fidelity over third-order coefficients but provides no meaningful predictive gain. An analytic history basis preserves useful adaptation more economically in a coupled identification task. With repeated slow poles, eight history coordinates meet normalized output error $10^{-4}$ across five fitted seeds despite substantial full-state error. Splitting the poles raises the smallest tested successful width to 64.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2611.19345 [cs.AI] |
| (or arXiv:2611.19345v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.19345 arXiv-issued DOI via DataCite |
Submission history
From: Khizar Qureshi [view email]
[v1]
Sat, 14 Nov 2026 11:34:00 UTC (121 KB)
[v2]
Tue, 17 Nov 2026 05:27:32 UTC (125 KB)
来源:arXiv cs.AI · arxiv.org