Automatic Optimization of Matrix Implementations for Distributed Machine Learning and Linear Algebra

Summary: Proposes automatic optimization of physical data layout for ML/LA, selecting among row/column, tiled, or relational representations to boost performance. Algorithms solve the layout-choice problem; a DBMS prototype yields speedups for ML/LA workloads. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6269
Venue: SIGMOD
Year: 2021
Pagerank: 5.9956597e-05
Overall Rank: 6,046 | 58.52%
DOI: 10.1145/3448016.3457317

Incoming Non-self Citations Over Time

Authors

1. Shangyu Luo (Rice University)
2. Dimitrije Jankov (Rice University)
3. Binhang Yuan (Rice University)
4. Chris Jermaine (Rice University)

BibTeX Citation

@inproceedings{luo_sigmod21,
        title = {{Automatic Optimization of Matrix Implementations for Distributed Machine Learning and Linear Algebra}},
        author = {Luo, Shangyu and Jankov, Dimitrije and Yuan, Binhang and Jermaine, Chris},
        series = {{SIGMOD} '21},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3448016.3457317},
        url = {https://dl.acm.org/doi/10.1145/3448016.3457317},
        year = {2021}
}

Incoming Citations (Sorted by Pagerank)

Showing 6 of 6 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
6,339	In-Database Machine Learning with CorgiPile: Stochastic Gradient Descent without Full Data Shuffle	2022	SIGMOD	5.907165e-05
8,794	AWARE: Workload-aware, Redundancy-exploiting Linear Algebra	2023	SIGMOD	5.370464e-05
9,542	Database as Runtime: Compiling LLMs to SQL for In-database Model Serving	2025	SIGMOD	5.2528121e-05
9,881	The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format	2024	SIGMOD	5.2040783e-05
10,410	TranSQL+: Serving Large Language Models with SQL on Low-Resource Hardware	2026	SIGMOD	5.093636e-05
11,561	Givens QR Decomposition over Relational Databases	2022	SIGMOD	5.093636e-05

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.

Rank	Cited Paper	Year	Venue	Pagerank
89	On the Propagation of Errors in the Size of Join Results	1991	SIGMOD	0.00035031529
151	Efficient Mid-Query Re-Optimization of Sub-Optimal Query Execution Plans	1998	SIGMOD	0.00029161879
288	Towards Estimation Error Guarantees for Distinct Values	2000	PODS	0.00022296371
415	SystemML: Declarative Machine Learning on Spark	2016	VLDB	0.0001888524
829	Proactive Re-Optimization	2005	SIGMOD	0.00013769838
993	Simulation of Database-Valued Markov Chains Using SimSQL	2013	SIGMOD	0.00012789598
1,644	Compressed Linear Algebra for Large-Scale Machine Learning	2016	VLDB	0.00010132912
2,217	Cumulon: Optimizing Statistical Data Analysis in the Cloud	2013	SIGMOD	8.9332438e-05
2,370	Declarative Recursive Computation on an RDBMS or, Why You Should Use a Database For Distributed Machine Learning	2019	VLDB	8.6795925e-05
2,681	Exploiting Matrix Dependency for Efficient Distributed Matrix Computation	2015	SIGMOD	8.2632778e-05
4,409	MNC: Structure-Exploiting Sparsity Estimation for Matrix Expressions	2019	SIGMOD	6.7178579e-05
9,572	PlinyCompute: A Platform for High-Performance, Distributed, Data-Intensive Tool Development	2018	SIGMOD	5.2528121e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	5,974	Towards instance-optimized data systems	2021	VLDB
2	3,459	A Comparative Evaluation of Systems for Scalable Linear Algebra-based Analytics	2018	VLDB
3	532	MLbase: A Distributed Machine-learning System	2013	CIDR
4	1,079	Hybrid Parallelization Strategies for Large-Scale Machine Learning in SystemML	2014	VLDB
5	9,840	Distributed Numerical and Machine Learning Computations via Two-Phase Execution of Aggregated Join Trees	2021	VLDB
6	8,617	Improving Matrix-vector Multiplication via Lossless Grammar-Compressed Matrices	2022	VLDB
7	11,669	Hybrid Evaluation for Distributed Iterative Matrix Computation	2021	SIGMOD
8	2,681	Exploiting Matrix Dependency for Efficient Distributed Matrix Computation	2015	SIGMOD
9	5,195	Tensor Relational Algebra for Distributed Machine Learning System Design	2021	VLDB
10	1,644	Compressed Linear Algebra for Large-Scale Machine Learning	2016	VLDB