AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Faster Boosting with Smaller Memory

Julaiti Alafate, Yoav S Freund

NeurIPS 2019 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 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
weighted sampling (Sparrow) instead of uniform sampling with XGBoost (ablation)boosted trees · CoverTypetest accuracyImproved
Sparrow vs XGBoost (external memory) on 8GB-15GB machinesSparrow · Splice sitetraining time: 3x longerImproved
Sparrow vs XGBoost and LightGBM when memory holds the full datasetSparrow · Splice sitetraining time: 1.3 -> 1.1 / 0.5Hurt
Sparrow vs XGBoost and LightGBMSparrow · Bathymetrytraining time: 0.4 -> 20.0 / 4.0Improved
Sparrow vs XGBoost and LightGBM on converged lossSparrow · Bathymetryexponential loss: 0.046 vs 0.054Improved
Sparrow vs LightGBM on converged lossSparrow · Splice siteexponential loss: 0.057 vs 0.053Hurt
initialize gamma to the maximum advantage of the previous tree's nodes and set a reasonable sample sizeSparrow · large datasetstraining timeImproved
less memory: 8GB instance vs 15GB instanceSparrow · Splice sitetraining time: 8.4 -> 2.9Improved

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