AI Paper Atlas

Research map / Time series / Long-term forecasting

An Algorithmic Framework for the Optimization of Deep Neural Networks Architectures and Hyperparameters

Julie Keisler, El-Ghazali Talbi, Sandra Claudel, Gilles Cabriel

JMLR 2024 · Time series › Long-term forecasting · approach: Spatiotemporal forecasting models · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use evolutionary search with joint mutation instead of random search (ablation)DRAGON · M1 MonthlyMASE: 1.098 -> 1.073Improved
use evolutionary search with joint mutation instead of random search (ablation)DRAGON · Tourism MonthlyMASE: 1.645 -> 1.450Improved
use evolutionary search with joint mutation instead of simulated annealing (ablation)DRAGON · M1 MonthlyMASE: 1.141 -> 1.073Improved
use evolutionary search with joint mutation instead of simulated annealing (ablation)DRAGON · Tourism MonthlyMASE: 2.640 -> 1.450Improved
joint instead of alternating architecture/hyperparameter mutation (ablation)DRAGON · M1 MonthlyMASE: 1.080 -> 1.073No clear effect
joint instead of alternating architecture/hyperparameter mutation (ablation)DRAGON · Tourism MonthlyMASE: 1.451 -> 1.450No clear effect
use random search instead of simulated annealing (ablation)DRAGON · Tourism MonthlyMASE: 2.640 -> 1.645Improved
add the training seed as a searched hyperparameter (ablation)DRAGON · M3 QuarterlyMASE: best MASE: 1.099Improved
add the training seed as a searched hyperparameter (ablation)DRAGON · Electricity WeeklyMASE: best MASE: 0.652Improved
DRAGON versus AutoGluon-TS ensembleDRAGON · Monash 27 datasetsdatasets won (MASE): 13 wins for AutoGluon, 14 lossesMixed
DRAGON versus AutoPytorchDRAGON · Monash 27 datasetsdatasets won (MASE): 7 wins for AutoPytorch, 20 lossesImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy