AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Efficient active learning of sparse halfspaces with arbitrary bounded noise

Chicheng Zhang, Jie Shen, Pranjal Awasthi

NeurIPS 2020 · 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 the proposed active algorithm instead of the prior efficient sparse-halfspace approachActive learning of sparse halfspaces under bounded noise · Isotropic log-concave distributionslabel complexityImproved
Use a noise-aware update that also updates on correctly predicted labelsOnline mirror descent refinement · Bounded-noise halfspace learningnoise toleranceImproved
Sample examples from a band around the current classifierOnline mirror descent refinement · Isotropic log-concave distributionslabel complexityImproved
Use sparsity-inducing online mirror descent regularizationProposed active learning algorithm · Sparse halfspaceslabel complexityImproved
Initialize by averaging labeled examples, hard-thresholding, then refiningProposed active learning algorithm · Sparse halfspaceslabel complexityMixed
Replace the noise-aware update with the negative Perceptron updateOnline mirror descent refinement · Bounded-noise halfspace learningbounded-noise toleranceHurt

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