ALPHABET：具有累积指数传输的拉普拉斯极点历史聚合器
ALPHABET: A Laplace-Pole History Aggregator with Banked Exponential Transport
- Korea Aerospace University（韩国航空大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
ALPHABET是一种紧凑线性时间模型，可将时间历史压缩为复极点模态，在82任务基准中平均排名3.97，6437个参数的推理与训练速度远超9个基准。
AI中文摘要：
序列模型能否仅用数千个参数和明确可审计的预测接口保持竞争力？我们提出ALPHABET，一种紧凑的线性时间模型，它将时间历史压缩为稳定的复极点模态：一个直接累积器将其模态状态综合回特征轨迹，一个独立的级联累积器分析变换后的轨迹而不进行再综合，一个仿射头仅从两个累积器中读取模态能量和滞后矩。我们表征该描述符保留的时间信息：对于平稳、完全观测的特征过程，每个模态能量是二阶谱的频率局部测量，此类测量的连续体可识别该谱，且几乎每个模态都能分离任意固定的有限组频谱不同的类别。在具有匹配低滞后统计的高斯控制任务上，学习到的描述符接近贝叶斯神谕，而原始自协方差仍处于随机水平。在固定的82任务注册表中，ALPHABET在完整的十家族比较中达到平均排名3.97。在通用宽度D=64的运行时基准下，其6437个参数的推理速度比9个基准平均快5.02倍，完整训练步骤平均快3.93倍。
英文摘要：
Can a sequence model remain competitive with only a few thousand parameters and an explicitly auditable prediction interface? We introduce ALPHABET, a compact linear-time model that compresses temporal history into stable complex pole modes: a direct bank synthesizes its modal states back into the feature trajectory, an independent cascaded bank analyzes the transformed trajectory without resynthesis, and an affine head reads only modal energies and lag moments from both banks. We characterize the temporal information this descriptor retains: for a stationary, fully observed feature process, each mode energy is a frequency-localized measurement of the second-order spectrum, the continuum of such measurements identifies the spectrum, and almost every mode separates any fixed finite set of spectrally distinct classes. On a Gaussian control with matched low-lag statistics, the learned descriptor approaches the Bayes oracle where raw autocovariances remain at chance. Across the fixed 82-task registry, ALPHABET attains mean rank 3.97 in the complete ten-family comparison. At the common-width D=64 runtime anchor, its 6,437 parameters deliver 5.02 times faster inference and 3.93 times faster complete training steps than the nine baselines on average.
