# HomeAdam: Adam and AdamW Algorithms Sometimes Go Home to Obtain Better Provable Generalization

Source: [HomeAdam: Adam and AdamW Algorithms Sometimes Go Home to Obtain Better Provable Generalization](<https://www.sota2.com/research/paper/69a7bc992d603e6de3e3d697>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-05T05:00:04.307Z

Authors: Feihu Huang, Guanyi Zhang, Songcan Chen

Published: 2026-03-03T06:29:24.000Z

## Abstract

Adam and AdamW are a class of default optimizers for training deep learning models in machine learning. These adaptive algorithms converge faster but generalize worse compared to SGD. In fact, their proved generalization error $O(\\frac{1}{\\sqrt{N}})$ also is larger than $O(\\frac{1}{N})$ of SGD, where $N$ denotes training sample size. Recently, although some variants of Adam have been proposed to improve its generalization, their improved generalizations are still unexplored in theory. To fill this gap, in the paper, we restudy generalization of Adam and AdamW via algorithmic stability, and first prove that Adam and AdamW without square-root (i.e., Adam(W)-srf) have a generalization error $O(\\frac{\\hat{\\rho}^{-2T}}{N})$, where $T$ denotes iteration number and $\\hat{\\rho}\>0$ denotes the smallest element of second-order momentum plus a small positive number. To improve generalization, we propose a class of efficient clever Adam (i.e., HomeAdam(W)) algorithms via sometimes returning momentum-based SGD. Moreover, we prove that our HomeAdam(W) have a smaller generalization error $O(\\frac{1}{N})$ than $O(\\frac{\\hat{\\rho}^{-2T}}{N})$ of Adam(W)-srf, since $\\hat{\\rho}$ is generally very small. In particular, it is also smaller than the existing $O(\\frac{1}{\\sqrt{N}})$ of Adam(W). Meanwhile, we prove our HomeAdam(W) have a faster convergence rate of $O(\\frac{1}{T^{1/4}})$ than $O(\\frac{\\breve{\\rho}^{-1}}{T^{1/4}})$ of the Adam(W)-srf, where $\\breve{\\rho}\\leq\\hat{\\rho}$ also is very small. Extensive numerical experiments demonstrate efficiency of our HomeAdam(W) algorithms.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Nonconvex Optimization on Nonconvex Optimization Theoretical](<https://www.sota2.com/research/sota/nonconvex-optimization-on-nonconvex-optimization-theoretical.md>): Nonconvex Optimization; Nonconvex Optimization Theoretical; Generalization Error: 1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.02649>)

[PDF](<https://arxiv.org/pdf/2603.02649.pdf>)
