LINEAiGE
AI HISTORY

Adam: A Method for Stochastic Optimization

Diederik P. Kingma and Jimmy Ba submitted 'Adam: A Method for Stochastic Optimization' on December 22, 2014. The paper introduces Adam, a first-order gradient-based optimization algorithm for stochastic objective functions based on adaptive estimates of lower-order moments.

December 22, 2014AI HISTORYVERIFIED

Historical classification

This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.

Why it matters

A documented optimization-method research milestone introducing Adam in the published research record.

People, organizations & technologies

PEOPLE
Diederik P. Kingma, Jimmy Ba

TECHNOLOGIES
Adam, Stochastic optimization, Gradient-based optimization, Adaptive moment estimation

Evidence & verification

STATE
verified

CONFIDENCE
high

LAST VERIFIED
2026-09-12T05:07:47+08:00

The original arXiv record establishes the authors, December 22 2014 first-submission date, title, and description of Adam as a first-order gradient-based optimization algorithm using adaptive estimates of lower-order moments. The University of Amsterdam research repository independently corroborates the authors, paper title, ICLR 2015 publication context, and core method description. The day-precision date is attached only to the arXiv submission milestone and is not asserted as a universal invention, release, or system-birth date. No geography, institutional affiliation, ancestry, influence, causality, or relationships are inferred.

Sources

SOURCE 1 · PRIMARY · CLAIM-EVIDENCE

Adam: A Method for Stochastic Optimization

arXiv

PUBLISHED
2014-12-22

SOURCE 2 · PRIMARY · CORROBORATION

Adam: A Method for Stochastic Optimization

University of Amsterdam

Trace the chronology

Record identity

LINEAiGE ID
adam-2014