Papers › Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule

Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule

9 Mar 2020arXiv:2003.03977archive 2025-07-28

Nikhil Iyer, V Thejas, Nipun Kwatra, Ramachandran Ramjee, Muthian Sivathanu

Several papers argue that wide minima generalize better than narrow minima. In this paper, through detailed experiments that not only corroborate the generalization properties of wide minima, we also provide empirical evidence for a new hypothesis that the density of wide minima is likely lower than the density of narrow minima. Further, motivated by this hypothesis, we design a novel explore-exploit learning rate schedule. On a variety of image and natural language datasets, compared to their original hand-tuned learning rate baselines, we show that our explore-exploit schedule can result in either up to 0.84% higher absolute accuracy using the original training budget or up to 57% reduced training time while achieving the original reported accuracy. For example, we achieve state-of-the-art (SOTA) accuracy for IWSLT'14 (DE-EN) dataset by just modifying the learning rate schedule of a high performing model.

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

nikhil-iyer-97/wide-minima-density-hypothesis officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
HA-Transformer/HA-Transformer mentioned in paperpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-branch Attentive Transformer (arXiv:2006.10270; that paper's own run record: 3 ran (of which 2 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-13 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning (arXiv:2212.08663; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP (arXiv:2210.09609; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. 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

Machine Translationde-en

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Machine Translation IWSLT2014 German-English Cutoff+Knee BLEU score 37.78 #8 of 34 Archive leaderboard report
Machine Translation WMT2014 German-English MAT+Knee BLEU score 31.9 #6 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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