English

Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity

Machine Learning 2025-06-12 v3

Abstract

Adam outperforms SGD when training language models. Yet this advantage is not well-understood theoretically -- previous convergence analysis for Adam and SGD mainly focuses on the number of steps TT and is already minimax-optimal in non-convex cases, which are both O~(T1/4)\widetilde{O}(T^{-1/4}). In this work, we argue that the exploitation of nice \ell_\infty-geometry is the key advantage of Adam over SGD. More specifically, we give a new convergence analysis for Adam under novel assumptions that loss is smooth under \ell_\infty-geometry rather than the more common 2\ell_2-geometry, which yields a much better empirical smoothness constant for GPT-2 and ResNet models. Our experiments confirm that Adam performs much worse when the favorable \ell_\infty-geometry is changed while SGD provably remains unaffected. We also extend the convergence analysis to blockwise Adam under novel blockwise smoothness assumptions.

Keywords

Cite

@article{arxiv.2410.08198,
  title  = {Adam Exploits $\ell_\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity},
  author = {Shuo Xie and Mohamad Amin Mohamadi and Zhiyuan Li},
  journal= {arXiv preprint arXiv:2410.08198},
  year   = {2025}
}