Research map / Architectures and efficiency / RNNs and normalization
Exploiting Dynamic Sparsity in Einsum
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies evaluating einsum expressions over sparse tensors whose sparsity is dynamic, exploiting it during evaluation rather than assuming fixed structure.
Problem
Evaluating einsum expressions is algorithmically hard and depends on tensor representation; dense arrays and coordinate lists (compact sparse representation) have different tradeoffs, especially when sparsity changes dynamically.
Approach
Exploits dynamic sparsity in einsum evaluation over coordinate-list representations; the abstract is truncated so the precise technique is not stated.
Closest papers by meaning
- Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines (NeurIPS 2024 · similarity 0.91)
- It's All Just Vectorization: einx, a Universal Notation for Tensor Operations (ICLR 2026 · similarity 0.87)
- Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods (NeurIPS 2024 · similarity 0.86)
- Nonparametric Decomposition of Sparse Tensors (ICML 2021 · similarity 0.86)
- Efficient Nonparametric Tensor Decomposition for Binary and Count Data (AAAI 2024 · similarity 0.84)
- Functional Complexity-adaptive Temporal Tensor Decomposition (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.