AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Scaling Simultaneous Optimistic Optimization for High-Dimensional Non-Convex Functions with Low Effective Dimensions

Hong Qian, Yang Yu

AAAI 2016 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 19 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
underestimate effective dimension (d=1 < de=2) (ablation)RESOO · 1000-d Braninsimple regret: 0.004 -> 3.816Hurt
use smaller estimated upper bound d (d=2 instead of d=4) at M=2 (ablation)RESOO · 1000-d Braninsimple regret: 0.075 -> 0.002Improved
increase restarts M from 1 to 2 (d=2) (ablation)RESOO · 1000-d Braninsimple regret: 0.004 -> 0.002Improved
increase restarts M from 4 to 10 (d=2) (ablation)RESOO · 1000-d Braninsimple regret: 0.001 -> 0.107Hurt
increase restarts M from 4 to 10 (d=4) (ablation)RESOO · 1000-d Rosenbrocksimple regret: 1.556 -> 2.691Hurt
random embedding with restarts (RESOO) instead of SOOSOO · rotated Branin and Rosenbrock, D=100 to 100000simple regretImproved
increase ambient dimension D from 100 to 100000RESOO · Branin and Rosenbrocksimple regretNo clear effect
use RESOO instead of SOO with separated hyper-parametersSOO · MNIST SVM tuningtest accuracy: 94.33% -> 94.81%Improved
use RESOO instead of SOO with separated hyper-parametersSOO · Letter SVM tuningtest accuracy: 85.06% -> 85.47%Improved
separate per-pair SVM hyper-parameters instead of one shared value (random search)multi-class SVM · MNISTtest accuracy: 93.75% -> 94.13%Improved
separate per-pair SVM hyper-parameters instead of shared value (SOO)SOO · MNISTtest accuracy: 94.61% -> 94.33%Hurt
larger effective-dimension estimate d2 vs d1 (ablation)RESOO · Vowel SVM tuningtest accuracy: 83.40% -> 83.16%Hurt

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