AI Paper Atlas

Research map / Bandits and online learning / Multi-armed bandits

Adam with Bandit Sampling for Deep Learning

Rui Liu, Tianyi Wu, Barzan Mozafari

NeurIPS 2020 · Bandits and online learning › Multi-armed bandits · approach: Bandit formulations for ML problems · 2 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
add bandit-based example sampling to Adam (Adambs) instead of uniform samplingAdam · CNN on CIFAR10 and CIFAR100training loss vs wall-clock timeImproved
add bandit-based example sampling to Adam (Adambs)Adam · CNN on Fashion MNISTtraining loss vs wall-clock timeMixed
add bandit-based example sampling to Adam (Adambs)Adam · LSTM on MNIST and Fashion MNISTtraining loss vs wall-clock timeImproved
add bandit-based example sampling to Adam (Adambs)Adam · RCNN on IMDBtraining loss vs wall-clock timeMixed
bandit sampling versus importance sampling on Adam (Adam-impt)Adam · CNN, RNN and RCNN benchmarkstraining loss vs wall-clock timeImproved
use Adam-based methods instead of basic SGD variants (SGD, Momentum, Adagrad, RMSprop)Adambs comparison · appendix CNN experimentstraining lossImproved
bandit sampling over individual examples versus Adam with adaptive or uniform sampling over prefixed batchesAdam · doubly heavy-tailed gradient distributionconvergence rate boundImproved
add bandit sampling when the d sqrt(T) term dominates the boundAdam · theoretical regret boundconvergence rateNo clear effect

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