AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Certificate-Guided Pruning for Stochastic Lipschitz Optimization

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

ICML 2026 · Optimization › Nonconvex and smooth optimization · approach: Adaptive first-order convex methods · 0 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
add GP refinement within the active set when local smoothness ratio rho < 0.5 (ablation)CGP · Branin (T=200)simple regret (x1e-2): 2.0 -> 1.4Improved
add GP refinement (hybrid) (ablation)CGP · Rosenbrock (T=200)simple regret (x1e-2): 3.8 -> 3.4Improved
add GP refinement (hybrid) on rough function (ablation)CGP · Needle-2D (T=200)simple regret (x1e-2): 1.2 -> 1.1No clear effect
replace GP-UCB with CGPGP-UCB · Needle-2D (non-differentiable)simple regret (x1e-2): 2.1 -> 1.2Improved
replace TuRBO with CGP-TR trust regions plus local certificatesTuRBO · Rover-60 (T=500)regret: 12.4 -> 11.2Improved
use CGP-TR instead of vanilla CGP for high dimensionCGP · d>20 benchmarkstractabilityImproved
initialize CGP-Adaptive with L underestimated by 100x (ablation)CGP-Adaptive · Hartmann-6simple regret (x1e-2): 2.9 -> 3.2Hurt
learn L online via doubling instead of LIPOLIPO · Hartmann-6simple regret (x1e-2): 6.2 -> 3.2Improved
remove pruning certificates (ablation)CGP · ablation (Table 8, not shown in text)regret: +78%Hurt
remove coverage penalty (ablation)CGP · ablation (Table 8, not shown in text)regret: +44%Hurt
remove replication (ablation)CGP · ablation (Table 8, not shown in text)regret: +33%Hurt
use certified eps_t stopping ruleCGP · stopping rule (Table 9)samples saved: 33% saved, no regret penaltyImproved

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