Learning Optimization

Weekly deep-dives into optimization theory — gradient methods, proximal algorithms, convergence analysis, and the math

Newsletter Published weekly

Join to Subscribe

Created by

chandu chowdary

Editions

Published on May 30, 2026
Report this article
Day 25 — RMSProp: Fixing AdaGrad’s “Memory Problem”

chandu chowdary on LinkedIn

0 comments

Like Comment Share
Published on May 25, 2026
Report this article
Day 24 — AdaGrad: Adapting Learning Rates from Data

chandu chowdary on LinkedIn

0 comments

Like Comment Share
Published on May 20, 2026
Report this article
Day 23 — Katyusha: Accelerating Variance Reduction with Momentum

chandu chowdary on LinkedIn

0 comments

Like Comment Share
Published on May 15, 2026
Report this article
Day 22 — SPIDER: Tracking Gradients with Near-Zero Variance

chandu chowdary on LinkedIn

0 comments

Like Comment Share
Published on May 10, 2026
Report this article
Day 21 — SARAH: Recursive Variance Reduction for Smarter Optimization

chandu chowdary on LinkedIn

0 comments

Like Comment Share

More from this author