AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Faster Algorithms and Constant Lower Bounds for the Worst-Case Expected Error

Jonah Brown-Cohen

NeurIPS 2021 · Learning theory and algorithms › Sample complexity · approach: Statistical-query lower bounds · 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 ℓ2 algorithm instead of subgroup estimationImportance sampling · Constant and Intergroup Varianceexpected squared error: 0.018 -> 0.052Hurt
Use the ℓ2 algorithm instead of reweightingImportance sampling · Intragroup Varianceexpected squared error: 0.100 -> 0.053Improved
Use the ℓ2 algorithm instead of reweightingImportance sampling · Worst Case ℓ∞ and Worst Case ℓ2expected squared error: 0.101 -> 0.062; 0.181 -> 0.078Improved
Use the ℓ2 algorithm instead of the sample meanSnowball sampling · Spatially Correlate Valuesexpected squared error: 0.082 -> 0.032Improved
Use the ℓ2 algorithm instead of the ℓ∞ algorithmSnowball sampling · Worst Case ℓ∞expected squared error: 0.135 -> 0.153Hurt
Use the ℓ2 algorithm instead of the ℓ∞ algorithmSnowball sampling · Worst Case ℓ2expected squared error: 0.327 -> 0.326Improved
Use the ℓ2 algorithm instead of the ℓ∞ algorithmSelective prediction · Worst Case ℓ∞expected squared error: 0.498 -> 0.620Hurt
Use the ℓ2 algorithm instead of the ℓ∞ algorithmSelective prediction · Worst Case ℓ2expected squared error: 0.746 -> 0.686Improved
Use the ℓ2 algorithm rather than the original ℓ∞ algorithmImportance sampling · Synthetic datasetsexpected squared error: 0.051 -> 0.052; 0.053 -> 0.052; 0.052 -> 0.053No 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