no code implementations • 11 Jun 2023 • Lyric Doshi, Vincent Zhuang, Gaurav Jain, Ryan Marcus, Haoyu Huang, Deniz Altınbüken, Eugene Brevdo, Campbell Fraser
We propose Kepler, an end-to-end learning-based approach to PQO that demonstrates significant speedups in query latency over a traditional query optimizer.
1 code implementation • 11 May 2022 • Andreas Kipf, Dominik Horn, Pascal Pfeil, Ryan Marcus, Tim Kraska
LSI works by building a learned index over a permutation vector, which allows binary search to performed on the unsorted base data using random access.
1 code implementation • 11 Aug 2021 • Mihail Stoian, Andreas Kipf, Ryan Marcus, Tim Kraska
Latest research proposes to replace existing index structures with learned models.
1 code implementation • 12 Oct 2020 • Min Du, Nesime Tatbul, Brian Rivers, Akhilesh Kumar Gupta, Lucas Hu, Wei Wang, Ryan Marcus, Shengtian Zhou, Insup Lee, Justin Gottschlich
Class distribution skews in imbalanced datasets may lead to models with prediction bias towards majority classes, making fair assessment of classifiers a challenging task.
no code implementations • 28 Sep 2020 • Fangke Ye, Shengtian Zhou, Anand Venkat, Ryan Marcus, Nesime Tatbul, Jesmin Jahan Tithi, Niranjan Hasabnis, Paul Petersen, Timothy G Mattson, Tim Kraska, Pradeep Dubey, Vivek Sarkar, Justin Gottschlich
First, MISIM uses a novel context-aware semantic structure (CASS), which is designed to aid in lifting semantic meaning from code syntax.
no code implementations • 21 Jul 2020 • Chi Zhang, Ryan Marcus, Anat Kleiman, Olga Papaemmanouil
In this extended abstract, we propose a new technique for query scheduling with the explicit goal of reducing disk reads and thus implicitly increasing query performance.
no code implementations • 5 Jun 2020 • Fangke Ye, Shengtian Zhou, Anand Venkat, Ryan Marcus, Nesime Tatbul, Jesmin Jahan Tithi, Niranjan Hasabnis, Paul Petersen, Timothy Mattson, Tim Kraska, Pradeep Dubey, Vivek Sarkar, Justin Gottschlich
Code semantics similarity can be used for many tasks such as code recommendation, automated software defect correction, and clone detection.
no code implementations • 30 Apr 2020 • Andreas Kipf, Ryan Marcus, Alexander van Renen, Mihail Stoian, Alfons Kemper, Tim Kraska, Thomas Neumann
Recent research has shown that learned models can outperform state-of-the-art index structures in size and lookup performance.
no code implementations • 24 Mar 2020 • Fangke Ye, Shengtian Zhou, Anand Venkat, Ryan Marcus, Paul Petersen, Jesmin Jahan Tithi, Tim Mattson, Tim Kraska, Pradeep Dubey, Vivek Sarkar, Justin Gottschlich
The simplified parse tree (SPT) presented in Aroma, a state-of-the-art code recommendation system, is a tree-structured representation used to infer code semantics by capturing program \emph{structure} rather than program \emph{syntax}.
1 code implementation • 21 Mar 2020 • Nadiia Chepurko, Ryan Marcus, Emanuel Zgraggen, Raul Castro Fernandez, Tim Kraska, David Karger
Our system has two distinct components: (1) a framework to search and join data with the input data, based on various attributes of the input, and (2) an efficient feature selection algorithm that prunes out noisy or irrelevant features from the resulting join.
1 code implementation • NeurIPS 2019 • Hongzi Mao, Parimarjan Negi, Akshay Narayan, Hanrui Wang, Jiacheng Yang, Haonan Wang, Ryan Marcus, Ravichandra Addanki, Mehrdad Khani Shirkoohi, Songtao He, Vikram Nathan, Frank Cangialosi, Shaileshh Venkatakrishnan, Wei-Hung Weng, Song Han, Tim Kraska, Dr.Mohammad Alizadeh
We present Park, a platform for researchers to experiment with Reinforcement Learning (RL) for computer systems.
1 code implementation • 29 Nov 2019 • Andreas Kipf, Ryan Marcus, Alexander van Renen, Mihail Stoian, Alfons Kemper, Tim Kraska, Thomas Neumann
A groundswell of recent work has focused on improving data management systems with learned components.
no code implementations • 25 Jan 2019 • Ryan Marcus, Olga Papaemmanouil
Integrating machine learning into the internals of database management systems requires significant feature engineering, a human effort-intensive process to determine the best way to represent the pieces of information that are relevant to a task.
no code implementations • 28 Feb 2018 • Ryan Marcus, Olga Papaemmanouil
However, modern query optimizers typically employ static join enumeration algorithms that do not receive any feedback about the quality of the resulting plan.
1 code implementation • 29 Jan 2016 • Ryan Marcus, Olga Papaemmanouil
Workload management for cloud databases must deal with the tasks of resource provisioning, query placement and query scheduling in a manner that meets the application's performance goals while minimizing the cost of using cloud resources.
Databases