AIRE-Prune：用于状态空间模型中状态剪枝的渐近脉冲响应能量
AIRE-Prune: Asymptotic Impulse-Response Energy for State Pruning in State Space Models
AI总结：
AIRE-Prune通过渐近脉冲响应能量评分实现状态空间模型的状态剪枝，有效降低计算成本并保持高精度。
摘要：
状态空间模型（SSMs）通常牺牲容量、搜索空间或稳定性来抵消大状态维度带来的内存和计算成本。我们提出了一种结构化的后训练剪枝方法用于SSMs——AIRE-Prune（渐近脉冲响应能量用于状态剪枝（PRUN(E））），该方法通过直接最小化长期输出能量失真来减少每层的状态维度。AIRE-Prune为每个状态分配一个闭式渐近脉冲响应能量基于的分数，即其在无限时间范围内贡献的总脉冲响应能量，并在层间归一化这些分数以实现全局跨层比较和选择。这将模式截断从单个系统扩展到深度栈，并使剪枝与渐近响应能量对齐，而非最坏情况增益。在多样化的序列基准测试中，AIRE-Prune在SISO和MIMO SSMs中揭示了显著的冗余性，平均剪枝率为60.8%，在不重新训练的情况下平均精度下降仅为0.29%，同时显著降低了计算量。代码：https://github.com/falcon-arrow/AIRE-Prune。
英文摘要：
State space models (SSMs) often sacrifice capacity, search space, or stability to offset the memory and compute costs of large state dimensions. We introduce a structured post-training pruning method for SSMs -- AIRE-Prune (Asymptotic Impulse-Response Energy for State PRUN(E)) -- that reduces each layer's state dimension by directly minimizing long-run output-energy distortion. AIRE-Prune assigns every state a closed-form asymptotic impulse-response energy-based score, i.e., the total impulse-response energy it contributes over an infinite horizon (time), and normalizes these scores layer-wise to enable global cross-layer comparison and selection. This extends modal truncation from single systems to deep stacks and aligns pruning with asymptotic response energy rather than worst-case gain. Across diverse sequence benchmarks, AIRE-Prune reveals substantial redundancy in SISO and MIMO SSMs with average pruning of 60.8%, with average accuracy drop of 0.29% without retraining, while significantly lowering compute. Code: https://github.com/falcon-arrow/AIRE-Prune.
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。
