HMAB: Self-Driving Hierarchy of Bandits for Integrated Physical Database Design Tuning

Summary: HMAB: a self-driving hierarchical multi-armed-bandit framework that jointly selects indices and materialized views, avoiding full combinatorial search via hierarchical pruning and strategic exploration using direct performance observations. Offers provable expected-performance guarantees and achieves up to 96% improvement over a state-of-the-art commercial physical-design tool on industrial benchmarks. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 13069
Venue: VLDB
Year: 2023
Pagerank: 5.2669029e-05
Overall Rank: 5,925 | 58.83%
DOI: 10.14778/3565816.3565824

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 8 of 8 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
7,332	Refactoring Index Tuning Process with Benefit Estimation	2024	VLDB	4.7553758e-05
8,003	The Holon Approach for Simultaneously Tuning Multiple Components in a Self-Driving Database Management System with Machine Learning via Synthesized Proto-Actions	2024	VLDB	4.6049527e-05
9,798	UniView: A Unified Autonomous Materialized View Management System for Various Databases	2024	VLDB	4.2777144e-05
9,931	Wii: Dynamic Budget Reallocation In Index Tuning	2024	SIGMOD	4.2469394e-05
10,032	Rainbow: Risk-aware Index Benefit Estimation Facing Out Of Distribution Workloads	2026	SIGMOD	4.1905499e-05
10,125	Understanding and Detecting Query Performance Regression in Practical Index Tuning: [Experiments & Analysis]	2026	SIGMOD	4.1905499e-05
10,552	Esc: An Early-Stopping Checker for Budget-aware Index Tuning	2025	VLDB	4.1905499e-05
11,024	SeLeP: Learning Based Semantic Prefetching for Exploratory Database Workloads	2024	VLDB	4.1905499e-05

Outgoing Citations (Sorted by Pagerank)

Showing 32 of 32 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
71	How Good Are Query Optimizers, Really?	2016	VLDB	0.00059446482
101	The Case for Learned Index Structures	2018	SIGMOD	0.00049778866
160	Automated Selection of Materialized Views and Indexes for SQL Databases	2000	VLDB	0.00040053897
203	Learned Cardinalities: Estimating Correlated Joins with Deep Learning	2019	CIDR	0.00034868567
237	An Efficient, Cost-Driven Index Selection Tool for Microsoft SQL Server	1997	VLDB	0.00031727601
258	DB2 Design Advisor: Integrated Automatic Physical Database Design	2004	VLDB	0.00030196528
371	Self-Driving Database Management Systems	2017	CIDR	0.00025382677
407	Database Cracking	2007	CIDR	0.00023941779
495	Automatic SQL Tuning in Oracle 10g	2004	VLDB	0.00021712703
517	AutoAdmin "What-if" Index Analysis Utility	1998	SIGMOD	0.00021193179
634	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00018844568
659	The Making of TPC-DS	2006	VLDB	0.00018514913
704	Query-based Workload Forecasting for Self-Driving Database Management Systems	2018	SIGMOD	0.00017785557
728	Optimizing Queries Using Materialized Views: A Practical, Scalable Solution	2001	SIGMOD	0.00017459654
876	Plan-Structured Deep Neural Network Models for Query Performance Prediction	2019	VLDB	0.00015660534
1,018	Automatic Physical Database Tuning: A Relaxation-based Approach	2005	SIGMOD	0.00014626746
1,110	Materialized View Selection and Maintenance Using Multi-Query Optimization	2001	SIGMOD	0.00013902997
1,346	NoDB: Efficient Query Execution on Raw Data Files	2012	SIGMOD	0.00012472598
1,365	FITing-Tree: A Data-aware Index Structure	2019	SIGMOD	0.00012379754
1,856	AI Meets AI: Leveraging Query Executions to Improve Index Recommendations	2019	SIGMOD	0.00010319105
2,022	Magic mirror in my hand, which is the best in the land? An Experimental Evaluation of Index Selection Algorithms	2020	VLDB	9.7623022e-05
2,050	Automatically Indexing Millions of Databases in Microsoft Azure SQL Database	2019	SIGMOD	9.6883066e-05
2,153	The Data Calculator*: Data Structure Design and Cost Synthesis from First Principles and Learned Cost Models	2018	SIGMOD	9.418541e-05
2,154	SkinnerDB: Regret-Bounded Query Evaluation via Reinforcement Learning	2018	VLDB	9.4176683e-05
2,467	CoPhy: A Scalable, Portable, and Interactive Index Advisor for Large Workloads	2011	VLDB	8.7264908e-05
2,788	To Tune or not to Tune? A Lightweight Physical Design Alerter	2006	VLDB	8.121027e-05
3,066	Learning a Partitioning Advisor for Cloud Databases	2020	SIGMOD	7.6255556e-05
3,580	Query Performance Prediction for Concurrent Queries using Graph Embedding	2020	VLDB	6.9460425e-05
3,658	Towards a Hands-Free Query Optimizer through Deep Learning	2019	CIDR	6.8700949e-05
4,730	UDO: Universal Database Optimization using Reinforcement Learning	2021	VLDB	5.9604983e-05
4,966	Releasing Cloud Databases from the Chains of Performance Prediction Models	2017	CIDR	5.7949047e-05
5,421	QUIET: Continuous Query-driven Index Tuning	2003	VLDB	5.5152497e-05

Semantically Similar Papers

Overall Rank	Paper	Year	Venue	Pagerank
3,276	Configuration-Parametric Query Optimization for Physical Design Tuning	2008	SIGMOD	7.2880761e-05
10,435	Automated Database Tuning vs. Human-Based Tuning in a Simulated Stressful Work Environment: A Demonstration of the Database Gym	2025	SIGMOD	4.1905499e-05
634	Bao: Making Learned Query Optimization Practical	2021	SIGMOD	0.00018844568
510	An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning	2019	SIGMOD	0.00021420477
4,235	CGPTuner: a Contextual Gaussian Process Bandit Approach for the Automatic Tuning of IT Configurations Under Varying Workload Conditions	2021	VLDB	6.3297728e-05
4,587	MB2: Decomposed Behavior Modeling for Self-Driving Database Management Systems	2021	SIGMOD	6.0594195e-05
3,077	Constrained Physical Design Tuning	2008	VLDB	7.6043371e-05
6,376	A Unified and Efficient Coordinating Framework for Autonomous DBMS Tuning	2023	SIGMOD	5.0861082e-05
5,834	An Efficient Transfer Learning Based Configuration Adviser for Database Tuning	2024	VLDB	5.3082111e-05
1,018	Automatic Physical Database Tuning: A Relaxation-based Approach	2005	SIGMOD	0.00014626746