EinDecomp: Decomposition of Declaratively-Specified Machine Learning and Numerical Computations for Parallel Execution
Summary: Extended Einstein summation as a declarative abstraction for tensor computations, enabling automatic intra-operator parallelism by rewriting any Einstein-specified op into an equivalent tensor-relational form. Generalizes data/model parallelism and formulates algorithms to compute optimal, device-aware tensor-relational decompositions for operator graphs. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Daniel Bourgeois
- 2. Zhimin Ding
- 3. Dimitrije Jankov
- 4. Jiehui Li
- 5. Mahmoud Sleem
- 6. Yuxin Tang
- 7. Jiawen Yao
- 8. Xinyu Yao
- 9. Chris Jermaine
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,279 | Galley: Modern Query Optimization for Sparse Tensor Programs | 2025 | SIGMOD | 4.5435639e-05 |
| 10,226 | Automated Tensor-Relational Decomposition for Large-Scale Sparse Tensor Computation | 2026 | VLDB | 4.1945683e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 12 of 12 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
Previous
Page 1 / 1
Next