Skip to results
MLSift
← Feed
routineTheory & OptimizationKaczmarz algorithm2606.29593

How AI settled the complexity of the oldest SGD algorithm

Michał Dereziński, Xiaoyu Dong

cs.LG cs.AI math.NA math.OC stat.ML

Abstract

In 1937, Stefan Kaczmarz proposed a simple algorithm for solving systems of linear equations. This algorithm turned out to be the earliest known example of stochastic gradient descent, a ubiquitous computing paradigm that drives the training of modern AI models such as ChatGPT and Gemini. Now, those AI models have joined forces to discover the worst-case complexity of the Kaczmarz algorithm. This paper tells the story of how it happened.

Topics

Classified with taxonomy v2 on Sat, 5 Sept 2026.

The PDF is 1–3 MB. Open it in your browser's viewer, or load it here.

Open PDF