madgrad

A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization algorithm. MADGRAD is a 'best-of-both-worlds' optimizer with the generalization performance of stochastic gradient descent and at least as fast convergence as that of Adam, often faster. A drop-in optim_madgrad() implementation is provided based on Defazio et al (2020) doi:10.48550/arXiv.2101.11075.

Last 30 days

This package has been downloaded 117 times in the last 30 days. Now we're getting somewhere! Enough downloads to populate a lively group chat. The following heatmap shows the distribution of downloads per day. Yesterday, it was downloaded 5 times.

The following line graph shows the downloads per day. You can hover over the graph to see the exact number of downloads per day.

Last 365 days

This package has been downloaded 1,632 times in the last 365 days. That's enough downloads to impress a room full of undergrads. A commendable achievement indeed. The day with the most downloads was Jan 22, 2025 with 29 downloads.

The following line graph shows the downloads per day. You can hover over the graph to see the exact number of downloads per day.