AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Stochastic $L^\natural$-convex Function Minimization

Haixiang Zhang, Zeyu Zheng, Javad Lavaei

NeurIPS 2021 · Learning theory and algorithms › Sample complexity · approach: Statistical-query lower bounds · 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 truncation step to projected SSGD (ablation)Algorithm 2 · Staffing allocation regularized d=4 N=10cost: 6.56e5 -> 2.99e5Improved
add truncation step (ablation)Algorithm 2 · Staffing allocation regularized d=24 N=10cost: 3.09e7 -> 1.50e7Improved
add truncation step (ablation)Algorithm 2 · Staffing allocation constrained d=4 N=10cost: 4.99e5 -> 3.00e5Improved
add truncation step (ablation)Algorithm 2 · Staffing allocation constrained d=24 N=10cost: 2.10e7 -> 1.36e7Improved
add truncation step (ablation)Algorithm 2 · Staffing allocation regularized d=4 N=50cost: 1.08e5 -> 5.34e4Improved
add truncation step (ablation)Algorithm 2 · Staffing allocation regularized d=4 N=10objective value: 2.11e2 -> 2.10e2No clear effect
add truncation step (ablation)Algorithm 2 · Staffing allocation constrained d=24 N=10objective value: 1.17e1 -> 9.43e0Mixed
increase dimension d from 2 to 20 at N=50Truncated subgradient · Separable convexcost (x10^7): 0.39 -> 1.69Hurt
increase dimension d from 2 to 20 at N=50Dimension reduction · Separable convexcost (x10^7): 0.19 -> 4.28Hurt
use dimension reduction instead of truncated subgradient, low dDimension reduction · Separable convex d=2 N=50cost (x10^7): 0.39 -> 0.19Improved
use dimension reduction instead of truncated subgradient, high dDimension reduction · Separable convex d=20 N=50cost (x10^7): 1.69 -> 4.28Hurt
increase N from 50 to 150 at d=2Dimension reduction · Separable convexcost (x10^7): 0.19 -> 0.25No clear effect

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