AI Paper Atlas

Research map / Optimization / Optimizers

Training Deep Models Faster with Robust, Approximate Importance Sampling

Tyler B Johnson, Carlos Guestrin

NeurIPS 2018 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 62 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 RAIS importance sampling with adaptive learning rate instead of uniform SGDSGD · SVHNvalidation error: 0.0226 -> 0.0201Improved
use RAIS importance sampling with adaptive learning rate instead of uniform SGDSGD · rot-MNISTvalidation error: 0.0512 -> 0.0476Improved
use RAIS importance sampling with adaptive learning rate instead of uniform SGDSGD · CIFAR-10validation error: 0.0607 -> 0.0590Improved
use RAIS importance sampling with adaptive learning rate instead of uniform SGDSGD · CIFAR-100validation error: 0.236 -> 0.236No clear effect
use RAIS importance sampling with adaptive learning rate instead of uniform SGDSGD · CIFAR-100training speed: approximately 20% speed-upImproved
use RAIS importance sampling with adaptive learning rate instead of uniform SGDSGD · SVHNtraining speed: more than 2xImproved
use exact oracle importance sampling instead of RAISRAIS-SGD · MNIST LeNettraining objectiveImproved

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