Vote NO!

Excited to share our new work! We introduce a dataset of tasks for learned optimizer research. As an example application of this dataset we meta-train lists of optimizer hyper parameters that work well on a diverse set of tasks. arxiv.org/abs/2002.11887 1/4

Finally, we have open sourced the code for the tasks as well as learning curves for ~29 million models trained with different optimizers and hyper parameters. github.com/google-researc… 3/4

exciting work: a dataset of tasks for learned optimizer research!

I need your help to share this handbook quickly to hospitals, doctors, nurses and anyone who needs to know around the world. It is available here: covid-19.alibabacloud.com. We are in this together! (2/2)

Physics computation itself acts as a regularizer while training the model embedded in it. Our results serve as proof-of-principle to smear the boundary between physics computation and ML. We are glad to share our work with you on Physical Review Letters #openaccess journals.aps.org/prl/abstract/1…

Fortunate to jointly work on this project with Ruoxi Sun Yanfei Chen Tomas Pfister Rui Zhang Sercan Arık. Paper Link: arxiv.org/pdf/2406.02818 Website Link: yuszh.com/chain-of-agent…