Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone

  • 类型:arxiv
  • 标识:2609.23087
  • 链接:https://arxiv.org/abs/2609.23087
  • 主分类:engineering
  • 形态:method
  • TLDR:Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for these decisions, #Params and #FLOPs, capture size and compute but not architectural structure: two architectures with identical parameter budgets but different depth-width, head, or FFN allocations receive identical scores yet behave differently. We propose Neural Spectral Capacity (NSC), a closed-form scalar grounded in the singular-value spectrum of each weight matrix. Under standard random initialization, the Marchenko-Pastur law renders NSC computable from the architectural
  • 待LLM分类:是
  • 来源文件:
  • /inbox/tom/_candidates/2026-09-25-agent-rag-longcontext-candidates.json