Filters








9,433 Hits in 6.5 sec

Learning to Optimize Join Queries With Deep Reinforcement Learning [article]

Sanjay Krishnan, Zongheng Yang, Ken Goldberg, Joseph Hellerstein, Ion Stoica
2019 arXiv   pre-print
Recognizing the link between classical Dynamic Programming enumeration methods and recent results in Reinforcement Learning (RL), we propose a new method for learning optimized join search strategies.  ...  Our extensive evaluation shows that DQ achieves plans with optimization costs and query execution times competitive with the native query optimizer in each system, but can execute significantly faster  ...  Our key insight is that join ordering has a deep algorithmic connection with Reinforcement Learning (RL) [47] . Join ordering's sequential structure is the same problem structure that underpins RL.  ... 
arXiv:1808.03196v2 fatcat:w35hsr6li5g23lbhnw6z3ueibe

Deep Reinforcement Learning for Join Order Enumeration

Ryan Marcus, Olga Papaemmanouil
2018 Proceedings of the First International Workshop on Exploiting Artificial Intelligence Techniques for Data Management - aiDM'18  
In this paper, we argue that existing deep reinforcement learning techniques can be applied to address this challenge.  ...  Join order selection plays a significant role in query performance.  ...  Here, we share our vision for a query optimizer based on deep reinforcement learning (DRL), a process by which a machine learns a task through continuous feedback with the help of a neural network.  ... 
doi:10.1145/3211954.3211957 dblp:conf/sigmod/MarcusP18 fatcat:jlu6usqdi5f25dvd7mpowkxezy

Towards a Hands-Free Query Optimizer through Deep Learning [article]

Ryan Marcus, Olga Papaemmanouil
2018 arXiv   pre-print
We identify potential complications for future research that integrates deep learning with query optimization, and we describe three novel deep learning based approaches that can lead the way to end-to-end  ...  In this vision paper, we argue that a new type of query optimizer, based on deep reinforcement learning, can drastically improve on the state-of-the-art.  ...  with an eye towards a more principled deep reinforcement learning powered query optimizer.  ... 
arXiv:1809.10212v2 fatcat:k4srbxjwy5fd7nd7nqdcwpnoci

Join Query Optimization with Deep Reinforcement Learning Algorithms [article]

Jonas Heitz, Kurt Stockinger
2019 arXiv   pre-print
Recent success of deep reinforcement learning (DRL) creates new opportunities for the field of query optimization to tackle the above-mentioned problems.  ...  Traditional query optimizers use dynamic programming (DP) methods combined with a set of rules and restrictions to avoid exhaustive enumeration of all possible join orders.  ...  We also want to thank Katharina Rombach for the many discussions about reinforcement learning.  ... 
arXiv:1911.11689v1 fatcat:oxdertk5frfynhmdnnt7td3hz4

Learning State Representations for Query Optimization with Deep Reinforcement Learning [article]

Jennifer Ortiz, Magdalena Balazinska, Johannes Gehrke, S. Sathiya Keerthi
2018 arXiv   pre-print
In the database field, query optimization remains a difficult problem. Our goal in this work is to explore the capabilities of deep reinforcement learning in the context of query optimization.  ...  We further discuss how we can use the state representation to improve query optimization using reinforcement learning.  ...  [11] uses a deep reinforcement learning technique to determine join order for a fixed database.  ... 
arXiv:1803.08604v1 fatcat:h2cytvx55re5hfzkdrg2l4gfoq

Neo

Ryan Marcus, Parimarjan Negi, Hongzi Mao, Chi Zhang, Mohammad Alizadeh, Tim Kraska, Olga Papaemmanouil, Nesime Tatbul
2019 Proceedings of the VLDB Endowment  
relies on deep neural networks to generate query executions plans.  ...  Neo bootstraps its query optimization model from existing optimizers and continues to learn from incoming queries, building upon its successes and learning from its failures.  ...  CONCLUSIONS This paper presents Neo, the first end-to-end learning optimizer that generates highly efficient query execution plans using deep neural networks.  ... 
doi:10.14778/3342263.3342644 fatcat:ep3tixgsbrdxhlt4ekm2flvc6u

Neo: A Learned Query Optimizer [article]

Ryan Marcus, Parimarjan Negi, Hongzi Mao, Chi Zhang, Mohammad Alizadeh, Tim Kraska, Olga Papaemmanouil, Nesime Tatbul
2019 arXiv   pre-print
relies on deep neural networks to generate query executions plans.  ...  Neo bootstraps its query optimization model from existing optimizers and continues to learn from incoming queries, building upon its successes and learning from its failures.  ...  This showcases the potential for a deep-learning powered query optimizer to keep up with changes in real-world query workloads.  ... 
arXiv:1904.03711v1 fatcat:sm5bmuavtvffrjkg5qno7pwaaq

Bao: Learning to Steer Query Optimizers [article]

Ryan Marcus, Parimarjan Negi, Hongzi Mao, Nesime Tatbul, Mohammad Alizadeh, Tim Kraska
2020 arXiv   pre-print
Bao combines modern tree convolutional neural networks with Thompson sampling, a decades-old and well-studied reinforcement learning algorithm.  ...  Recent efforts to apply machine learning techniques to query optimization challenges have been promising, but have shown few practical gains due to substantive training overhead, inability to adapt to  ...  Applications requiring faster planning time may wish to consider other options [66] . Comparison with Neo Neo [39] is an end-to-end query optimizer based on deep reinforcement learning.  ... 
arXiv:2004.03814v1 fatcat:zprpgewcsbfzzfpz5iscxh7yai

A View on Deep Reinforcement Learning in System Optimization [article]

Ameer Haj-Ali, Nesreen K. Ahmed, Ted Willke, Joseph Gonzalez, Krste Asanovic, Ion Stoica
2019 arXiv   pre-print
We propose a set of essential metrics to guide future works in evaluating the efficacy of using deep reinforcement learning in system optimization.  ...  These problems with delayed and often sequentially aggregated reward, are often inherently reinforcement learning problems and present the opportunity to leverage the recent substantial advances in deep  ...  For example, in query join order optimization, the number of joins is finite and known from the query.  ... 
arXiv:1908.01275v3 fatcat:ih52psaazzcs3pulz4nnnjk2di

Machine Learning for Database Management Systems

Sai Tanishq N
2020 International Journal Of Engineering And Computer Science  
Machine Learning (ML) is transforming the world with research breakthroughs that are leading to the progress of every field. We are living in an era of data explosion.  ...  The models are capable of correlating a dataset and its features with an accuracy that humans fail to achieve.  ...  ReJoin [12] and Neo [13] use recent advancements in deep reinforcement learning to generate optimal QEPs.  ... 
doi:10.18535/ijecs/v9i08.4520 fatcat:rqs2wvlslzegxkg6skltnmqyl4

Efficient RDF Graph Storage based on Reinforcement Learning [article]

Lei Zheng, Ziming Shen, Hongzhi Wang
2020 arXiv   pre-print
To address the difficult problem, this paper adopts reinforcement learning (RL) to optimize the storage partition method of RDF graph based on the relational database.  ...  We transform the graph storage into a Markov decision process, and develop the reinforcement learning algorithm for graph storage design.  ...  Double Deep Q-Network Deep Learning Network Since in reinforcement learning, our observational data is ordered, step by step, using such data to update the parameters of the neural network in DQN will  ... 
arXiv:2010.11538v1 fatcat:76edszi4g5cf7lo7m3bpuuvwe4

Scalable Multi-Query Execution using Reinforcement Learning

Panagiotis Sioulas, Anastasia Ailamaki
2021 Proceedings of the 2021 International Conference on Management of Data  
RouLette scales by replacing sharing-aware optimization with adaptive query processing, and it chooses opportunities to explore and exploit by using reinforcement learning.  ...  Sharing work across queries presents an opportunity to reduce the total cost of processing and therefore improve throughput with increasing query load.  ...  It progressively explores sharing opportunities using a heuristic based on reinforcement learning. RouLette also proposes optimizations that reduce the adaptation overhead.  ... 
doi:10.1145/3448016.3452799 fatcat:sjt5akmfufc37honzmywh7e5jq

A Survey on Deep Reinforcement Learning for Data Processing and Analytics [article]

Qingpeng Cai, Can Cui, Yiyuan Xiong, Wei Wang, Zhongle Xie, Meihui Zhang
2022 arXiv   pre-print
Recently, reinforcement learning, deep reinforcement learning (DRL) in particular, is increasingly explored and exploited in many areas because it can learn better strategies in complicated environments  ...  it is interacting with than statically designed algorithms.  ...  The DRL agent could learn to understand and solve various tasks with the right incentives. First, we introduce basic foundations and practical techniques in DRL.  ... 
arXiv:2108.04526v3 fatcat:kcusgp7jzfbf7ov5os7gwf2e6i

Balsa: Learning a Query Optimizer Without Expert Demonstrations [article]

Zongheng Yang, Wei-Lin Chiang, Sifei Luan, Gautam Mittal, Michael Luo, Ion Stoica
2022 arXiv   pre-print
We present Balsa, a query optimizer built by deep reinforcement learning.  ...  On the Join Order Benchmark, Balsa matches the performance of two expert query optimizers, both open-source and commercial, with two hours of learning, and outperforms them by up to 2.8× in workload runtime  ...  Balsa leverages deep reinforcement learning (RL), which has been successfully employed to learn complex skills [3] and exceed human experts at playing games [26, 27, 33] .  ... 
arXiv:2201.01441v1 fatcat:pfahwbg35bb4dombbjf2xfm5e4

QTune

Guoliang Li, Xuanhe Zhou, Shifu Li, Bo Gao
2019 Proceedings of the VLDB Endowment  
To address these problems, we propose a query-aware database tuning system QTune with a deep reinforcement learning (DRL) model, which can efficiently and effectively tune the database configurations.  ...  We propose a Double-State Deep Deterministic Policy Gradient (DS-DDPG) model to enable query-aware database configuration tuning, which utilizes the actor-critic networks to tune the database configurations  ...  We utilize the deep reinforcement learning model, which combines reinforcement learning and neural networks to automatically learn the knob values from limited samples.  ... 
doi:10.14778/3352063.3352129 fatcat:6l7joisrvbacnaids5ucur4li4
« Previous Showing results 1 — 15 out of 9,433 results