Papers › Parameter Re-Initialization through Cyclical Batch Size Schedules

Parameter Re-Initialization through Cyclical Batch Size Schedules

4 Dec 2018arXiv:1812.01216archive 2025-07-28

Norman Mu, Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael Mahoney

Optimal parameter initialization remains a crucial problem for neural network training. A poor weight initialization may take longer to train and/or converge to sub-optimal solutions. Here, we propose a method of weight re-initialization by repeated annealing and injection of noise in the training process. We implement this through a cyclical batch size schedule motivated by a Bayesian perspective of neural network training. We evaluate our methods through extensive experiments on tasks in language modeling, natural language inference, and image classification. We demonstrate the ability of our method to improve language modeling performance by up to 7.91 perplexity and reduce training iterations by up to 61%, in addition to its flexibility in enabling snapshot ensembling and use with adversarial training.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

General ClassificationImage ClassificationLanguage ModelingLanguage ModellingNatural Language Inferenceimage-classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Inference SNLI CBS-1 + ESIM % Test Accuracy 86.73 #51 of 98 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