no code implementations • 8 Apr 2024 • Taiyi Wang, Eiko Yoneki
This study introduces the Instance-Aware Index Advisor (IA2), a novel deep reinforcement learning (DRL)-based approach for optimizing index selection in databases facing large action spaces of potential candidates.
no code implementations • 25 Mar 2024 • Guoliang He, Eiko Yoneki
In this work, we explore the possibility of GPU native instruction optimization to further push the CUDA kernels to extreme performance.
1 code implementation • 28 Apr 2023 • Guoliang He, Sean Parker, Eiko Yoneki
Tensor graph superoptimisation systems perform a sequence of subgraph substitution to neural networks, to find the optimal computation graph structure.
1 code implementation • 8 Mar 2023 • Guoliang He, Zak Singh, Eiko Yoneki
Rewrite systems [6, 10, 12] have been widely employing equality saturation [9], which is an optimisation methodology that uses a saturated e-graph to represent all possible sequences of rewrite simultaneously, and then extracts the optimal one.
1 code implementation • 3 May 2022 • Sean Parker, Sami Alabed, Eiko Yoneki
Our proposed approach RLFlow can learn to perform neural network subgraph transformations, without the need for expertly designed heuristics to achieve a high level of performance.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 16 Dec 2021 • Sami Alabed, Eiko Yoneki
Then it applies the expert-provided knowledge to the graph to further contextualize the system behavior.
no code implementations • 20 Apr 2021 • Oliver Hope, Eiko Yoneki
We explore the feasibility of combining Graph Neural Network-based policy architectures with Deep Reinforcement Learning as an approach to problems in systems.
no code implementations • 30 Mar 2021 • Sami Alabed, Eiko Yoneki
The model is then incorporated in a standard Bayesian Optimization loop to find parameters that maximize RocksDB's IO throughput.
no code implementations • 16 Sep 2019 • Jeremy Welborn, Michael Schaarschmidt, Eiko Yoneki
Configuration spaces for computer systems can be challenging for traditional and automatic tuning strategies.
no code implementations • 15 Sep 2019 • Michael Schaarschmidt, Kai Fricke, Eiko Yoneki
Reinforcement learning frameworks have introduced abstractions to implement and execute algorithms at scale.
1 code implementation • 21 Oct 2018 • Michael Schaarschmidt, Sven Mika, Kai Fricke, Eiko Yoneki
Reinforcement learning (RL) tasks are challenging to implement, execute and test due to algorithmic instability, hyper-parameter sensitivity, and heterogeneous distributed communication patterns.
4 code implementations • 23 Aug 2018 • Michael Schaarschmidt, Alexander Kuhnle, Ben Ellis, Kai Fricke, Felix Gessert, Eiko Yoneki
In this work, we introduce LIFT, an end-to-end software stack for applying deep reinforcement learning to data management tasks.
no code implementations • 1 Dec 2016 • Valentin Dalibard, Michael Schaarschmidt, Eiko Yoneki
We present an optimizer which uses Bayesian optimization to tune the system parameters of distributed stochastic gradient descent (SGD).
no code implementations • 31 Oct 2016 • Michael Schaarschmidt, Felix Gessert, Valentin Dalibard, Eiko Yoneki
This paper investigates the use of deep reinforcement learning for runtime parameters of cloud databases under latency constraints.