TY - JOUR
T1 - A Demonstration of Willump
T2 - A Statistically-Aware End-to-end Optimizer for Machine Learning Inference
AU - Kraft, Peter
AU - Kang, Daniel
AU - Narayanan, Deepak
AU - Palkar, Shoumik
AU - Bailis, Peter
AU - Zaharia, Matei
N1 - Publisher Copyright:
© VLDB Endowment. All rights reserved.
PY - 2020
Y1 - 2020
N2 - Systems for ML inference are widely deployed today, but they typically optimize ML inference workloads using techniques designed for conventional data serving workloads and miss critical opportunities to leverage the statistical nature of ML. In this demo, we present Willump, an optimizer for ML inference that introduces statistically-motivated optimizations targeting ML applications whose performance bottleneck is feature computation. Willump automatically cascades feature computation for classification queries: Willump classifies most data inputs using only high-value, low-cost features selected by a cost model, improving query performance by up to 5× without statistically significant accuracy loss. In this demo, we use interactive and easily-downloadable Jupyter notebooks to show VLDB attendees which applications Willump can speed up, how to use Willump, and how Willump produces such large performance gains.
AB - Systems for ML inference are widely deployed today, but they typically optimize ML inference workloads using techniques designed for conventional data serving workloads and miss critical opportunities to leverage the statistical nature of ML. In this demo, we present Willump, an optimizer for ML inference that introduces statistically-motivated optimizations targeting ML applications whose performance bottleneck is feature computation. Willump automatically cascades feature computation for classification queries: Willump classifies most data inputs using only high-value, low-cost features selected by a cost model, improving query performance by up to 5× without statistically significant accuracy loss. In this demo, we use interactive and easily-downloadable Jupyter notebooks to show VLDB attendees which applications Willump can speed up, how to use Willump, and how Willump produces such large performance gains.
UR - http://www.scopus.com/inward/record.url?scp=85135085111&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85135085111&partnerID=8YFLogxK
U2 - 10.14778/3415478.3415487
DO - 10.14778/3415478.3415487
M3 - Article
AN - SCOPUS:85135085111
SN - 2150-8097
VL - 13
SP - 2833
EP - 2836
JO - Proceedings of the VLDB Endowment
JF - Proceedings of the VLDB Endowment
IS - 12
ER -