PofoliaShared via Pofolia

arXiv (Cornell University)· 2019· Preprint

On the Convergence of Adam and Beyond

Sashank J. Reddi, Satyen Kale, Sanjiv Kumar

Short summary

This paper identifies the exponential moving average in popular deep learning optimizers like Adam as a cause of convergence failure in certain settings, proposing new variants with 'long-term memory' that fix these issues and improve performance.

AI-generated from the title and abstract; the full text is not read.

TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways, key points and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Field: Philosophy

PhilosophyArts and Humanities