{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:35:09Z","timestamp":1760027709313,"version":"3.44.0"},"reference-count":7,"publisher":"Association for Computing Machinery (ACM)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2020,8]]},"abstract":"<jats:p>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 x 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.<\/jats:p>","DOI":"10.14778\/3415478.3415487","type":"journal-article","created":{"date-parts":[[2020,9,14]],"date-time":"2020-09-14T18:46:35Z","timestamp":1600109195000},"page":"2833-2836","source":"Crossref","is-referenced-by-count":6,"title":["A demonstration of willump"],"prefix":"10.14778","volume":"13","author":[{"given":"Peter","family":"Kraft","sequence":"first","affiliation":[{"name":"Stanford DAWN Project"}]},{"given":"Daniel","family":"Kang","sequence":"additional","affiliation":[{"name":"Stanford DAWN Project"}]},{"given":"Deepak","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Stanford DAWN Project"}]},{"given":"Shoumik","family":"Palkar","sequence":"additional","affiliation":[{"name":"Stanford DAWN Project"}]},{"given":"Peter","family":"Bailis","sequence":"additional","affiliation":[{"name":"Stanford DAWN Project"}]},{"given":"Matei","family":"Zaharia","sequence":"additional","affiliation":[{"name":"Stanford DAWN Project"}]}],"member":"320","published-online":{"date-parts":[[2020,8]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2556195.2556252"},{"key":"e_1_2_1_2_1","first-page":"613","volume-title":"Clipper: A Low-Latency Online Prediction Serving System. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI17)","author":"Crankshaw D.","year":"2017","unstructured":"D. Crankshaw, X. Wang, G. Zhou, M. J. Franklin, J. E. Gonzalez, and I. Stoica. Clipper: A Low-Latency Online Prediction Serving System. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI17), pages 613--627, 2017."},{"key":"e_1_2_1_3_1","first-page":"1","volume-title":"Deep Feature Synthesis: Towards Automating Data Science Endeavors. In 2015 IEEE International Conference on Data Science and Advanced Analytics, DSAA 2015","author":"Kanter J. M.","year":"2015","unstructured":"J. M. Kanter and K. Veeramachaneni. Deep Feature Synthesis: Towards Automating Data Science Endeavors. In 2015 IEEE International Conference on Data Science and Advanced Analytics, DSAA 2015, Paris, France, October 19-21, 2015, pages 1--10. IEEE, 2015."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415487"},{"key":"e_1_2_1_5_1","first-page":"611","volume-title":"PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Lee Y.","year":"2018","unstructured":"Y. Lee, A. Scolari, B. Chun, M. Santambrogio, M. Weimer, and M. Interlandi. PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18), pages 611--626, 2018."},{"key":"e_1_2_1_6_1","first-page":"1002","volume-title":"Evaluating End-to-End Optimization for Data Analytics Applications in Weld","author":"Palkar S.","year":"2018","unstructured":"S. Palkar, J. Thomas, D. Narayanan, P. Thaker, R. Palamuttam, P. Negi, A. Shanbhag, M. Schwarzkopf, H. Pirk, S. Amarasinghe, et al. Evaluating End-to-End Optimization for Data Analytics Applications in Weld. volume 11, pages 1002--1015. VLDB Endowment, 2018."},{"key":"e_1_2_1_7_1","volume-title":"Rapid Object Detection Using a Boosted Cascade of Simple Features. page 511","author":"Viola P.","year":"2001","unstructured":"P. Viola and M. Jones. Rapid Object Detection Using a Boosted Cascade of Simple Features. page 511. IEEE, 2001."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3415478.3415487","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T02:18:26Z","timestamp":1758075506000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3415478.3415487"}},"subtitle":["a statistically-aware end-to-end optimizer for machine learning inference"],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":7,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2020,8]]}},"alternative-id":["10.14778\/3415478.3415487"],"URL":"https:\/\/doi.org\/10.14778\/3415478.3415487","relation":{},"ISSN":["2150-8097"],"issn-type":[{"type":"print","value":"2150-8097"}],"subject":[],"published":{"date-parts":[[2020,8]]}}}