Topic · Artificial Intelligence · Computer Science

Stochastic Gradient Optimization Techniques

OpenAlex topic; a paper is listed when OpenAlex scores it at least 0.5 for this topic.

Neuroscience·bioRxivPreprint·Aug 16, 2018
Want to read
An Adaptive Optimizer without User-Specified Hyperparameters through Historical Projection and Self-Calibrated Scaling
Kazunori D. Yamada
This paper introduces YamAdam, an adaptive optimizer with no user-specified hyperparameters, and shows it outperforms 30 other optimizer settings across multiple tasks.
4 citations
deep learning·benchmarking
·𝕏 Post·Bluesky