AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Learnability of Linear Thresholds from Label Proportions

Rishi Saket

NeurIPS 2021 · Learning theory and algorithms › Sample complexity · approach: Learning halfspaces under noise · 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
Increase dimension d from 10 to 100Algorithm A · Uncorrelated random bags, m=50avg s/t: 2.162 -> 1.533Hurt
Increase dimension d from 10 to 100Algorithm A · Uncorrelated random bags, m=200avg s/t: 2.479 -> 1.297Hurt
Increase number of bags m from 50 to 200Algorithm A · Uncorrelated random bags, d=10avg s/t: 2.162 -> 2.479Improved
Increase number of bags m from 50 to 200Algorithm A · Uncorrelated random bags, d=100avg s/t: 1.533 -> 1.297Hurt
Use Algorithm A instead of best random linear thresholdAlgorithm A · Uncorrelated random bags, d=10, m=200avg r/s: 0.688Improved
Use Algorithm A instead of best random linear thresholdAlgorithm A · Uncorrelated random bags, d=100, m=200avg r/s: 0.994No clear effect
Use correlated bag geometry instead of iid pointsAlgorithm A · Correlated bags, d=100, m=50avg s/t: 1.533 -> 2.460Improved
Use correlated bag geometry instead of iid pointsrandom linear threshold · d=10, m=50avg r/s: 0.847 -> 0.049Hurt
Use correlated bag geometry instead of iid pointsAlgorithm A · d=10, m=50min s/t: 1.714 -> 1.200Mixed
Algorithm A vs theoretical guarantee on synthetic instancesAlgorithm A · Uncorrelated random bags, d=100, m=200avg s/t: 1.297Improved

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