AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification

John T Halloran, David M Rocke

NeurIPS 2020 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 1 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
GPU-optimize TRON-LR by decoupling sequential dependencies and reducing transfersTRON-LR · Sparse TRON-LR benchmarksaverage training time improvement over single-threaded TRON-LR: 70.8%Improved
combine GPU optimization with multithreadingTRON-LR · Sparse TRON-LR benchmarksaverage training time improvement over single-thread-optimized TRON: 89.2%Improved
combine GPU optimization with multithreadingTRON-LR · Sparse TRON-LR benchmarksaverage training time improvement over multithread-optimized TRON: 65.2%Improved
use the direct GPU implementation with the original variable access pattern (ablation)TRON-LR · SUSYspeedup: 0.65Hurt
use the mixed GPU and multithread architectureTRON-LR · Sparse TRON-LR benchmarksaverage speedup: 9.3 foldImproved
use the GPU-optimized SVM solverPercolator SVM learning · Kimspeedup over original Percolator SVM learning engine: 7.4 foldImproved
use the mixed GPU and multithread SVM solverPercolator SVM learning · Kimspeedup over original Percolator SVM learning engine: 6.6 foldImproved
use the mixed GPU and multithread SVM solverPercolator SVM learning · Wilhelmspeedup over original Percolator SVM learning engine: 5.4 foldImproved
move dense SVM computations to GPU while using multithreading for memory-intensive active-set operationsPercolator SVM learning · WilhelmSVM learning time: 4.4 days -> 19.7 hoursImproved
use PyTorch GPU gradient descent rather than CPU gradient descentPyTorch logistic regression · rcv1GPU speedup: 14.63Improved
use PyTorch GPU L-BFGS rather than CPU L-BFGSPyTorch logistic regression · rcv1GPU speedup: 13.08Improved

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