AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Algorithms and Hardness for Learning Linear Thresholds from Label Proportions

Rishi Saket

NeurIPS 2022 · 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
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] bags · small margin, d=10, m=50avg % bags satisfied: 6.3 -> 93.0Improved
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] bags · small margin, d=10, m=100avg % bags satisfied: 4.4 -> 97.1Improved
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] bags · small margin, d=40, m=50avg % bags satisfied: 4.8 -> 81.9Improved
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] bags · small margin, d=40, m=100avg % bags satisfied: 4.4 -> 83.0Improved
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] test · small margin, d=10, m=100instance-level test accuracy (%): 53.2 -> 98.6Improved
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] test · small margin, d=40, m=100instance-level test accuracy (%): 52.0 -> 90.1Improved
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] bags · large margin, d=10, m=50avg % bags satisfied: 46.3 -> 51.0Improved
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] bags · large margin, d=10, m=100avg % bags satisfied: 46.5 -> 55.9Improved
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] bags · large margin, d=40, m=100avg % bags satisfied: 40.9 -> 40.2No clear effect
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] test · large margin, d=40, m=50instance-level test accuracy (%): 53.2 -> 52.9No clear effect
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] test · large margin, d=10, m=100instance-level test accuracy (%): 63.1 -> 75.1Improved
use the SDP rounding algorithm instead of a random LTFLLP-LTF[3] bags · large margin, d=40, m=50avg % bags satisfied: 41.2 -> 43.5Mixed

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