AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Gradient Boosts the Approximate Vanishing Ideal

Hiroshi Kera, Yoshihiko Hasegawa

AAAI 2020 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 7 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 gradient normalization instead of coefficient normalizationSBC · D1 and D2runtime (ms): 48.0e+1 -> 13.4; 17.5e+3 -> 11.4Improved
Use gradient normalization instead of coefficient normalizationSBC · D1 and D2number of basis polynomials: 41 -> 30; 70 -> 33Improved
Use gradient normalization instead of coefficient normalizationSBC · Iriserror: 0.03 -> 0.04Hurt
Use gradient normalization instead of coefficient normalizationSBC · Vowelerror: 0.33 -> 0.45Hurt
Use gradient normalization instead of coefficient normalizationSBC · Vehicleerror: 0.22 -> 0.16Improved
Add gradient-based basis reduction (ablation)SBC-n_g · Irisfeature dimensionality: 148 -> 24.4Improved
Add gradient-based basis reduction (ablation)SBC-n_g · Iriserror: 0.04 -> 0.08Hurt
Add gradient-based basis reduction (ablation)SBC-n_g · Vowelfeature dimensionality: 3033 -> 254Improved
Add gradient-based basis reduction (ablation)SBC-n_g · Vowelerror: 0.45 -> 0.40Improved
Add gradient-based basis reduction (ablation)SBC-n_g · Vehiclefeature dimensionality: 5223 -> 260Improved
Add gradient-based basis reduction (ablation)SBC-n_g · Vehicleerror: 0.16 -> 0.25Hurt
Apply the proposed gradient-based reduction to the VCA and SBC-n_g polynomial bases (ablation)VCA and SBC-n_g · Four-point noise-free vanishing-ideal examplenumber of vanishing polynomials: VCA: five -> two; SBC-n_g: four -> twoImproved

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