AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly

Yuchen Jin, Tianyi Zhou, Liangyu Zhao, Yibo Zhu, Chuanxiong Guo, Marco Canini, Arvind Krishnamurthy

ICLR 2021 · Probabilistic and scientific modeling › Bayesian optimization · approach: Multi-fidelity hyperparameter optimization · 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 stage-wise Bayesian optimization with exponential loss forecasting instead of the original hand-tuned learning-rate scheduleResNet-50 · ImageNettraining-step speedup: 1.22×Improved
use stage-wise Bayesian optimization with exponential loss forecasting instead of the original hand-tuned learning-rate scheduleTransformer base · WMT 2014 English-Germantraining-step speedup: 1.43×Improved
use stage-wise Bayesian optimization with exponential loss forecasting instead of the original hand-tuned learning-rate scheduleBERT_BASE · BERT pre-trainingtraining-step speedup: 1.5×Improved
add exponential forecasting to predict loss at the full stage horizon rather than using loss at τ′ (ablation)AutoLRS · VGG-16, CIFAR-10top-1 accuracy: 91.73%, 92.59%, 92.24%Improved
use Bayesian optimization instead of random search (ablation)AutoLRS with exponential forecasting · VGG-16, CIFAR-10average top-1 accuracy: 0.09%Improved
use Bayesian optimization instead of grid search (ablation)AutoLRS with exponential forecasting · VGG-16, CIFAR-10average top-1 accuracy: 0.24%Improved
use Bayesian optimization instead of grid search (ablation)AutoLRS with exponential forecasting · VGG-16, CIFAR-100mean top-1 accuracy: 73.05%±0.14%; 72.63%±0.56%Improved
use AutoLRS instead of the hand-tuned scheduleBERT_BASE · MRPC Devaccuracy: 86.5 -> 88.0Improved
use AutoLRS instead of the hand-tuned scheduleBERT_BASE · MNLI Devaccuracy: 82.2 -> 82.5Improved
use AutoLRS instead of the hand-tuned scheduleBERT_BASE · CoLA Devaccuracy: 47.8 -> 47.6Hurt
use AutoLRS instead of the hand-tuned scheduleBERT_BASE · SQuAD v1.1 DevF1: 87.0 -> 87.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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