all AI news
Towards Learning Universal Hyperparameter Optimizers with Transformers. (arXiv:2205.13320v1 [cs.LG])
May 27, 2022, 1:11 a.m. | Yutian Chen, Xingyou Song, Chansoo Lee, Zi Wang, Qiuyi Zhang, David Dohan, Kazuya Kawakami, Greg Kochanski, Arnaud Doucet, Marc'aurelio Ranzato,
stat.ML updates on arXiv.org arxiv.org
Meta-learning hyperparameter optimization (HPO) algorithms from prior
experiments is a promising approach to improve optimization efficiency over
objective functions from a similar distribution. However, existing methods are
restricted to learning from experiments sharing the same set of
hyperparameters. In this paper, we introduce the OptFormer, the first
text-based Transformer HPO framework that provides a universal end-to-end
interface for jointly learning policy and function prediction when trained on
vast tuning data from the wild. Our extensive experiments demonstrate that the
OptFormer …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Scientist (m/f/x/d)
@ Symanto Research GmbH & Co. KG | Spain, Germany
Data Operations Analyst
@ Workday | Poland, Warsaw
Reference Data Specialist - Operations Analyst
@ JPMorgan Chase & Co. | Bengaluru, Karnataka, India
Data Scientist (Redwood City)
@ Anomali | Redwood City, CA
Software Engineer, Database - Languages & Relational Technologies
@ YugabyteDB | United States (Remote) or Sunnyvale, CA
Data Analyst (m/f/d) Online Marketing
@ StepStone Group | Düsseldorf, Germany