New AdamX optimizer integrates cosine similarity for adaptive gradient descent

Researchers have introduced AdamX, a novel first-order optimizer that integrates cosine similarity to adaptively control update magnitudes. This method is designed to be scalable, model-agnostic, and easily integrated into existing training pipelines. AdamX also features a variance rectification scheme to improve optimization smoothness in early training stages, demonstrating competitive convergence rates on various benchmarks. AI

IMPACT Introduces a new optimization technique that could improve training efficiency and convergence for various machine learning models.

RANK_REASON The cluster contains a research paper detailing a new optimization algorithm for machine learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv Recommender
• Litmaps
• ScienceCast
• scite Smart Citations

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →