Neural Optimizer Benchmark Dataset
- kaggle.com
zipUpdated Jan 28, 2026
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCiteRhythm_Ghai (2026). Neural Optimizer Benchmark Dataset [Dataset]. https://www.kaggle.com/datasets/rhythmghai/neural-optimizer-benchmark-dataset/codezip(16993 bytes)Available download formatsDataset updatedJan 28, 2026AuthorsRhythm_GhaiLicenseAttribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
License information was derived automaticallyDescriptionA research-grade dataset of optimizer "fingerprints" extracted from neural network training runs across multiple datasets, architectures, and random seeds.
Each row represents a full training run and includes stability metrics, sharpness and curvature statistics, gradient noise estimates, learning rate regime features, and generalization gap.
Designed for: - Meta-learning - AutoML research - Early optimizer selection - Training regime discovery - Optimization benchmarking
- p
ACM Transactions on Architecture and Code Optimization (TACO) Journal...
- pjip.org
Updated Jun 16, 2026ShareFacebookTwitterEmailClick to copy linkLink copiedCitePJIP (2026). ACM Transactions on Architecture and Code Optimization (TACO) Journal Metadata, Rankings, & Metrics [Dataset]. https://www.pjip.org/journal/1010599/acm-transactions-on-architecture-and-code-optimization-taco-Dataset updatedJun 16, 2026Dataset authored and provided byPJIPLicenseAttribution-NonCommercial 4.0 (CC BY-NC 4.0)https://creativecommons.org/licenses/by-nc/4.0/
License information was derived automaticallyVariables measuredFWCI Impact Score, Research Integrity RiskDescriptionComplete dataset containing the academic profile, journal ranking, indexing metrics, and publication metadata for ACM Transactions on Architecture and Code Optimization (TACO) Journal (Computer Science) [ISSN: 1544-3566].
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailNeural Optimizer Benchmark Dataset
Learning How Neural Networks Learn — A Meta-Dataset for Optimizer Selection
Attribution-ShareAlike 4.0 (CC BY-SA 4.0)https://creativecommons.org/licenses/by-sa/4.0/
License information was derived automatically
A research-grade dataset of optimizer "fingerprints" extracted from neural network training runs across multiple datasets, architectures, and random seeds.
Each row represents a full training run and includes stability metrics, sharpness and curvature statistics, gradient noise estimates, learning rate regime features, and generalization gap.
Designed for: - Meta-learning - AutoML research - Early optimizer selection - Training regime discovery - Optimization benchmarking