AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

PAC Learning Linear Thresholds from Label Proportions

Anand Paresh Brahmbhatt, Rishi Saket, Aravindan Raghuveer

NeurIPS 2023 · Learning theory and algorithms › Sample complexity · approach: Optimal mean estimation and subsampling · 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
use A2 instead of random LTF baselineLLP LTF learner · N(0,Sigma), d=10, q=2, k=1test accuracy: 78.26 -> 98.12Improved
use A2 instead of SDP algorithm for q=2LLP LTF learner · N(0,Sigma), d=10, q=2, k=1test accuracy: 88.40 -> 98.12Improved
use A2 instead of SDP algorithm for q=3LLP LTF learner · N(0,Sigma), d=10, q=3, k=1test accuracy: 67.31 -> 98.27Improved
use A2 instead of SDP algorithm at higher dimensionLLP LTF learner · N(0,Sigma), d=50, q=2, k=1test accuracy: 57.83 -> 95.64Improved
use A2 instead of SDP algorithm on general GaussianLLP LTF learner · N(mu,Sigma), d=10, q=2, k=1test accuracy: 90.10 -> 98.18Improved
use A2 instead of SDP algorithm on general Gaussian, d=50LLP LTF learner · N(mu,Sigma), d=50, q=3, k=1test accuracy: 62.39 -> 95.6Improved
use A2 instead of random LTF at large bag sizeLLP LTF learner · N(0,Sigma), d=50, q=50, k=25test accuracy: 55.76 -> 95.16Improved
use A2 instead of random LTF on general GaussianLLP LTF learner · N(mu,Sigma), d=10, q=50, k=35test accuracy: 62.86 -> 97.6Improved
increase dimension from 10 to 50Algorithm A2 · N(0,Sigma), q=2, k=1test accuracy: 98.12 -> 95.64Hurt
increase bag size q from 2 to 50 (balanced-ish bags)Algorithm A2 · N(0,Sigma), d=10test accuracy: 98.12 -> 97.87No clear effect
increase bag size q from 2 to 50 at d=50Algorithm A2 · N(0,Sigma), d=50test accuracy: 95.64 -> 95.16Hurt
use non-centered general Gaussian instead of centered GaussianAlgorithm A2 · d=50, q=10, k=8test accuracy: 94.34 -> 94.44No 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