AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Near-Optimal Active Learning of Halfspaces via Query Synthesis in the Noisy Setting

Lin Chen, Hamed Hassani, Amin Karbasi

AAAI 2017 · Learning theory and algorithms › Sample complexity · approach: Learning halfspaces under noise · 15 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 dimension coupling instead of prior methodsSynthetic halfspace learning, noiseless setting · Noiseless synthetic halfspace queriesestimation errorImproved
Use dimension coupling instead of prior methodsSynthetic halfspace learning, noisy setting · Noisy synthetic halfspace queriesestimation error: around two orders of magnitude smallerImproved
Use dimension coupling instead of repetitive queryingSynthetic halfspace learning · Noisy synthetic halfspace queries, ρ=0.2, d=1000estimation error: three orders of magnitude smallerImproved
Use dimension coupling instead of repetitive queryingSynthetic halfspace learning · Noisy synthetic halfspace queriesexecution timeHurt
Use dimension coupling instead of random sampling, uncertainty sampling, or query-by-committeeSynthetic halfspace learning · Noisy synthetic halfspace queriesexecution time: around 100 times fasterImproved
Use dimension coupling instead of version-space ellipsoid searchSynthetic halfspace learning · Noisy synthetic halfspace queriesestimation errorImproved
Combine two-dimensional subproblems through dimension couplingDimension Coupling (DC) · Noisy synthetic halfspace queriesestimation error: 5 ε (d-1)Improved

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