all AI news
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. (arXiv:2203.05482v2 [cs.LG] UPDATED)
June 23, 2022, 1:13 a.m. | Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S. Morcos, Hongseok Namkoong, Ali Farhadi, Yair C
cs.CV updates on arXiv.org arxiv.org
The conventional recipe for maximizing model accuracy is to (1) train
multiple models with various hyperparameters and (2) pick the individual model
which performs best on a held-out validation set, discarding the remainder. In
this paper, we revisit the second step of this procedure in the context of
fine-tuning large pre-trained models, where fine-tuned models often appear to
lie in a single low error basin. We show that averaging the weights of multiple
models fine-tuned with different hyperparameter configurations often …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Data Scientist (m/f/x/d)
@ Symanto Research GmbH & Co. KG | Spain, Germany
Enterprise Data Quality, Senior Analyst
@ Toyota North America | Plano
Data Analyst & Audit Management Software (AMS) Coordinator
@ World Vision | Philippines - Home Working
Product Manager Power BI Platform Tech I&E Operational Insights
@ ING | HBP (Amsterdam - Haarlerbergpark)
Sr. Director, Software Engineering, Clinical Data Strategy
@ Moderna | USA-Washington-Seattle-1099 Stewart Street
Data Engineer (Data as a Service)
@ Xplor | Atlanta, GA, United States