Skip to content
AI Atlas
PaperActive

AdamX: Cosine similarity meets gradient descent

arxiv.org/abs/2609.11867

Updated 30 min ago · first seen 11 Sept 2026

paper_01M294FPENHERCQJ53BZ4V8K55

Published
11 Sept 2026
T1 · 31 min ago
arXiv
2609.11867
T1 · 31 min ago
Category
cs.LG
T1 · 31 min ago

Abstract

We introduce AdamX, a first-order optimizer that incorporates cosine similarity as an adaptive mechanism for controlling update magnitudes. The proposed method is scalable, model-agnostic, and straightforward to integrate into existing training pipelines. We further introduce a variance rectification scheme that promotes smoother optimization during the early stages of training. Overall, we provide empirical evidence that AdamX achieves competitive convergence rates across a range of benchmark datasets and architectures. Performance is evaluated in terms of the number of epochs required to reach predefined performance thresholds under a fixed hyperparameter budget. Code and Experiments available at: https://github.com/FranciscoCaldas/adamX.

Authors 3

Francisco Caldas, Ruben Belo, Cl\'audia Soares

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 31 min agohigh

Arxiv announce type
new

Source:arXiv (Atom API + RSS)T1observed 31 min agohigh

arXiv id
2609.11867

Source:arXiv (Atom API + RSS)T1observed 31 min agohigh

Categories
cs.LG, math.OC

Source:arXiv (Atom API + RSS)T1observed 31 min agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 31 min agohigh

Primary category
cs.LG

Source:arXiv (Atom API + RSS)T1observed 31 min agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 31 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

31 min ago

Conflicts

None