all AI news
Implicit Bias of AdamW: $\ell_\infty$ Norm Constrained Optimization
April 9, 2024, 4:41 a.m. | Shuo Xie, Zhiyuan Li
cs.LG updates on arXiv.org arxiv.org
Abstract: Adam with decoupled weight decay, also known as AdamW, is widely acclaimed for its superior performance in language modeling tasks, surpassing Adam with $\ell_2$ regularization in terms of generalization and optimization. However, this advantage is not theoretically well-understood. One challenge here is that though intuitively Adam with $\ell_2$ regularization optimizes the $\ell_2$ regularized loss, it is not clear if AdamW optimizes a specific objective. In this work, we make progress toward understanding the benefit of …
abstract adam arxiv bias challenge cs.lg however language math.oc modeling norm optimization performance regularization stat.ml tasks terms type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Software Engineer, Machine Learning (Tel Aviv)
@ Meta | Tel Aviv, Israel
Senior Data Scientist- Digital Government
@ Oracle | CASABLANCA, Morocco