提出S³框架，统一定义和实现各类结构化稀疏模式。
S$^3$: Structured Sparsity Specification
- 用视图、块和作用域三组件定义稀疏结构，支持跨张量协同剪枝。
- 基于S³的剪枝方法在输出重建上超越经典二阶启发式方法。
- 适用于从细粒度到粗粒度的各种稀疏模式，兼容OBD和Surgeon。
我们提出结构化稀疏规范（S³），一种用于定义、组合和实现结构化稀疏模式的代数框架。S³通过三个组件指定稀疏性：通过布局组合重排张量的视图（View）、定义原子剪枝单元的块（Block）规范，以及稀疏决策作用域（Scope）。块与作用域均支持跨张量耦合，实现协调剪枝。S³可精确表达从细粒度N:M模式到粗粒度通道剪枝等多样稀疏结构，并与最优大脑损伤（OBD）和外科医生（OBS）无缝集成。我们数学形式化该框架，展示了其在典型稀疏模式上的表达能力，并通过完全基于S³构建的结构化OBS和OBD实验验证其有效性，在常见配置下输出重建性能优于成熟二阶启发式方法。
原文摘要 · Abstract (English)
We introduce the Structured Sparsity Specification (S$^3$), an algebraic framework for defining, composing, and implementing structured sparse patterns. S$^3$ specifies sparsity through three components: a View that reshapes the tensor via layout composition, a Block specification that defines the atomic pruning unit, and the sparsity decision Scope. Both Block and Scope support Coupling across tensors for coordinated sparsification. S$^3$ enables precise specification of diverse sparsity structures, from fine-grained N:M patterns to coarse channel pruning, and integrates seamlessly with Optimal Brain Damage (OBD) and Surgeon (OBS). We formalize the framework mathematically, demonstrate its expressiveness on canonical patterns, and validate it experimentally via structured OBS and OBD implementations built entirely on S$^3$, which surpasses well-established second order heuristics on output reconstruction across common configurations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。