SageDB: A Learned Database System

Summary: SageDB replaces general-purpose DBMS internals with application-specialized, learned models that jointly capture data distribution, workload, and hardware to synthesize optimal access methods and query plans. These models are embedded via code synthesis into core components for end-to-end specialization. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: hd947d0e66838447b
Venue: CIDR
Year: 2019
Pagerank: 0.00016506678
Overall Rank: 555 | 96.28%
DOI: -

Incoming Non-self Citations Over Time

Authors

1. Tim Kraska (Google; Massachusetts Institute of Technology)
2. Mohammad Alizadeh (Massachusetts Institute of Technology)
3. Alex Beutel (Google)
4. Ed H. Chi (Google)
5. Jialin Ding (Massachusetts Institute of Technology)
6. Ani Kristo (Brown University)
7. Guillaume Leclerc (Massachusetts Institute of Technology)
8. Samuel Madden (Massachusetts Institute of Technology)
9. Hongzi Mao (Massachusetts Institute of Technology)
10. Vikram Nathan (Massachusetts Institute of Technology)

BibTeX Citation

@inproceedings{kraska_cidr19,
        address = {Amsterdam, Netherlands},
        series = {{CIDR} '19},
        title = {{SageDB: A Learned Database System}},
        booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
        author = {Kraska, Tim and Alizadeh, Mohammad and Beutel, Alex and Chi, Ed H. and Ding, Jialin and Kristo, Ani and Leclerc, Guillaume and Madden, Samuel and Mao, Hongzi and Nathan, Vikram},
        year = {2019}
}

Incoming Citations (Sorted by Pagerank)

Showing 13 of 63 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
8,346	SparkCruise: Workload Optimization in Managed Spark Clusters at Microsoft	2021	VLDB	5.3510511e-05
8,385	NeurDB: On the Design and Implementation of an AI-powered Autonomous Database	2025	CIDR	5.3420959e-05
8,480	Deep Learning: Systems and Responsibility	2021	SIGMOD	5.333141e-05
8,532	AirIndex: Versatile Index Tuning Through Data and Storage	2023	SIGMOD	5.3217474e-05
9,020	Optimizing the cloud? Don't train models. Build oracles!	2024	CIDR	5.2355482e-05
9,115	Check Out the Big Brain on BRAD: Simplifying Cloud Data Processing with Learned Automated Data Meshes	2023	VLDB	5.2271833e-05
9,706	Database Gyms	2023	CIDR	5.1376763e-05
10,043	The Image Calculator: 10x Faster Image-AI Inference by Replacing JPEG with Self-designing Storage Format	2024	SIGMOD	5.0921006e-05
10,183	DumpKV: Learning based lifetime aware garbage collection for key value separation in LSM-tree	2025	VLDB	5.0651993e-05
10,217	DBMS Fitting: Why should we learn what we already know?	2020	CIDR	5.0582281e-05
10,475	LINE: A Learned Index with Group-Enhanced Leaves and Cache-Optimized Inner Tree	2026	SIGMOD	4.9793485e-05
10,844	Rethinking Learned Index and LSM-tree Integration	2026	VLDB	4.9793485e-05
10,856	How Much Can RocksDB Chew? Achieving Near-Zero Write Stalls with Sustainable RocksDB	2026	VLDB	4.9793485e-05

Outgoing Citations (Sorted by Pagerank)

Showing 17 of 17 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
1	Access Path Selection in a Relational Database Management System	1979	SIGMOD	0.0023947656
5	Optimal Aggregation Algorithms for Middleware [Extended Abstract]	2001	PODS	0.0010679641
12	C-Store: A Column-oriented DBMS	2005	VLDB	0.00068998927
20	Similarity Search in High Dimensions via Hashing	1999	VLDB	0.00057568153
40	The Case for Learned Index Structures	2018	SIGMOD	0.00046284649
78	Automatic Database Management System Tuning Through Large-scale Machine Learning	2017	SIGMOD	0.00036684414
85	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00035864347
123	Schism: a Workload-Driven Approach to Database Replication and Partitioning	2010	VLDB	0.00030762995
151	An Efficient, Cost-Driven Index Selection Tool for Microsoft SQL Server	1997	VLDB	0.00028672526
195	Integrating Vertical and Horizontal Partitioning into Automated Physical Database Design	2004	SIGMOD	0.00025628849
243	Automating Physical Database Design in a Parallel Database	2002	SIGMOD	0.00023358891
322	Tuning Database Configuration Parameters with iTuned	2009	VLDB	0.00021041865
343	Model-Driven Data Acquisition in Sensor Networks	2004	VLDB	0.00020519525
1,605	The Data Calculator*: Data Structure Design and Cost Synthesis from First Principles and Learned Cost Models	2018	SIGMOD	0.00010093796
1,842	On Predictive Modeling for Optimizing Transaction Execution in Parallel OLTP Systems	2012	VLDB	9.526552e-05
2,027	Database Learning: Toward a Database that Becomes Smarter Every Time	2017	SIGMOD	9.1618139e-05
4,862	iTuned: A Tool for Configuring and Visualizing Database Parameters	2010	SIGMOD	6.3786959e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	2,981	WiSeDB: A Learning-based Workload Management Advisor for Cloud Databases	2016	VLDB
2	4,741	Machine Learning for Databases	2021	VLDB
3	11,130	OpenMLDB: A Real-Time Relational Data Feature Computation System for Online ML	2025	SIGMOD
4	5,454	SeeDB: Visualizing Database Queries Efficiently	2014	VLDB
5	6,080	From Auto-tuning One Size Fits All to Self-designed and Learned Data-intensive Systems	2019	SIGMOD
6	9,182	DBSeer: Pain-free Database Administration through Workload Intelligence	2015	VLDB
7	10,179	Adaptive Schema Databases	2017	CIDR
8	4,059	Database-Agnostic Workload Management	2019	CIDR
9	318	DeepDB: Learn from Data, not from Queries!	2020	VLDB
10	7,598	SageDB: An Instance-Optimized Data Analytics System	2022	VLDB