AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

A Unified Formulation and Fast Accelerated Proximal Gradient Method for Classification

Naoki Ito, Akiko Takeda, Kim-Chuan Toh

JMLR 2017 · Optimization › Nonconvex and smooth optimization · approach: Stochastic variance reduction · 23 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 bisection instead of breakpoint search for the projection (ablation)FAPG · Projection, n=1,000,000, range [0,10]naverage runtime (msec): 94.2 -> 49.9Improved
use bisection instead of breakpoint search for the projection (ablation)FAPG · Projection, n=100,000, range [0,10]naverage runtime (msec): 8.3 -> 4.9Improved
add the decreasing strategy (dec) to backtracking and restart (ablation)FAPG nu-SVM · Artificial (m,n,nu)=(10000,1000,0.5)convergence stabilityMixed
add the stabilizing strategy (st) on top of bt+re+dec (ablation)FAPG nu-SVM · Artificial (m,n,nu)=(10000,1000,0.5)convergence stabilityImproved
add the final strategy (mt) on top of bt+re+dec+st (ablation)FAPG nu-SVM · Artificial (m,n,nu)=(10000,1000,0.5)optimality violationImproved
add all acceleration strategies instead of exact Lipschitz constant (ablation)FAPG nu-SVM · Artificial (m,n,nu)=(10000,1000,0.5)constant L_k: 3.61x10^4 -> 3.68x10^2Improved
add 'mt' strategy (ablation)FAPG logistic regression · a8a (C=10)violation below 10^-6 within 10000 iterationsImproved
decrease xi from 10^-2 to 10^-3 in approximate logistic regression (ablation)FAPG logistic regression · Artificialaccuracy: 99.8% -> 100.0%Improved
decrease xi from 10^-2 to 10^-3 in approximate logistic regression (ablation)FAPG logistic regression · mushroomsaccuracy: 99.4% -> 100.0%Improved
use FAPG logistic regression with bias instead of LIBLINEAR without biasFAPG · Artificialaccuracy: 85.2% -> 100.0%Improved
use FAPG instead of LIBSVM and SeDuMi on large datasets (linear kernel)FAPG nu-SVM · Benchmark datasets with m >= 50000computation timeImproved
use RBF kernel instead of linear kernel (ablation)FAPG nu-SVM · Benchmark datasetsruntimeHurt

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