Back to timeline

Research · September 1951

A Stochastic Approximation Method

Robbins and Monro showed how to find the root of a function from noisy measurements by taking small steps of decreasing size.

Why it matters

The step conditions derived here are still the ones a learning-rate schedule is chosen against.

The paper is framed as mathematical statistics and does not mention machine learning. It sets the requirement on the step sequence: the sum diverges, the sum of squares converges. Convergence proofs for gradient descent on noisy estimates rest on this result.

Event record

Event date
September 1951
Timeline date
Event date
Verification
Sources gathered automatically · September 17, 2026
Lines
ID
evt-0072

The September 1951 issue of the Annals of Mathematical Statistics.

Sources

Records that link to this one