构建预测视界:序列计算权衡下的参数共享分块预测
Compose the Horizon: Parameter-Shared Blockwise Forecasting under a Sequential-Compute Trade-off
AI总结:
本文提出递归函数分解(RFD)方法,通过参数共享分块预测实现长视界预测,在24项跨协议测试中23项优于基线,仅需0.08-0.46M参数。
摘要:
大多数长视界预测器一次性输出完整的未来序列。本文探究是否可复用紧凑算子输出连续的未来分块,以存储参数换取序列计算。递归函数分解(RFD)将视界映射分解为三个参数共享的分块预测,这些分块占据不相交的未来区间并进行拼接,而非作为趋势、季节或残差分量相加;每个输出分块会加入滚动上下文,用于后续算子应用的条件输入。在三种子实验中,移除前向反馈会损害所有四个评估数据集,而阻断前向反馈的梯度影响则几乎无变化,说明有用信号是演化的预测状态本身;复用共享算子的效果始终优于其他方式,但提升幅度小于扩大算子规模。该模型参数规模为0.08至0.46M,但其逐通道序列执行在高通道数时比迭代基线更慢且内存占用更高。在与十个强基线家族的冻结长上下文评估中,RFD在24个测试单元中的23个取得更低测试误差;该比较为跨协议比较,RFD使用512/720步上下文,基线使用96步上下文。
英文摘要:
Most long-horizon forecasters emit the complete future in one pass. We ask whether a compact operator can instead be reused to emit contiguous future blocks, trading stored parameters for sequential computation. Recursive Functional Decomposition (RFD) factorizes the horizon mapping into three parameter-shared block predictions. The blocks occupy disjoint future intervals and are concatenated, not added as trend, seasonal, or residual components, and each emitted block joins the rolling context that conditions the next application. In controlled three-seed experiments, removing forward feedback hurts all four evaluated datasets while stopping gradients through it changes little, so the useful signal is the evolving forecast state itself; reapplying the shared operator helps consistently, but by less than widening it. The model uses 0.08--0.46M parameters, yet its sequential channel-wise execution is slower and more memory-intensive than an iterative baseline at high channel count. In a frozen long-context evaluation against ten strong baseline families, RFD records lower test error in 23 of 24 cells; the comparison is cross-protocol, with RFD using 512/720-step context and the baselines using 96.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。