Papers › The Marginal Value of Adaptive Gradient Methods in Machine Learning

The Marginal Value of Adaptive Gradient Methods in Machine Learning

23 May 2017NeurIPS 2017 12arXiv:1705.08292archive 2025-07-28

Ashia C. Wilson, Rebecca Roelofs, Mitchell Stern, Nathan Srebro, Benjamin Recht

Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural networks. Examples include AdaGrad, RMSProp, and Adam. We show that for simple overparameterized problems, adaptive methods often find drastically different solutions than gradient descent (GD) or stochastic gradient descent (SGD). We construct an illustrative binary classification problem where the data is linearly separable, GD and SGD achieve zero test error, and AdaGrad, Adam, and RMSProp attain test errors arbitrarily close to half. We additionally study the empirical generalization capability of adaptive methods on several state-of-the-art deep learning models. We observe that the solutions found by adaptive methods generalize worse (often significantly worse) than SGD, even when these solutions have better training performance. These results suggest that practitioners should reconsider the use of adaptive methods to train neural networks.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

jrzech/reproduce-chexnet mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning (arXiv:1711.05225; that paper's own run record: 29 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 1 violated, 22 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
pasta41/deception mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hyperparameter Optimization Is Deceiving Us, and How to Stop It (arXiv:2102.03034; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
vrunm/text-classification-financial-phrase-bank mentioned on GitHubpytorchMITSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BIG-bench Machine LearningBinary Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdaGradAdamRMSPropSGD

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections