AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Worst-Case Analysis for Randomly Collected Data

Justin Chen, Gregory Valiant, Paul Valiant

NeurIPS 2020 · 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 SDP-derived estimator instead of inverse proportional reweightingSDP Alg · Importance sampling, worst-case boundexpected squared error: 0.101 -> 0.053Improved
Use SDP-derived estimator instead of subgroup estimationSDP Alg · Importance sampling, worst-case boundexpected squared error: 0.122 -> 0.053Improved
Use SDP Alg instead of subgroup estimation when values are constantSDP Alg · Importance sampling, constant valuesexpected squared error: 0.018 -> 0.051Hurt
Use SDP Alg instead of subgroup estimation on intergroup varianceSDP Alg · Importance sampling, intergroup varianceexpected squared error: 0.018 -> 0.053Hurt
Use SDP Alg instead of subgroup estimation on intragroup varianceSDP Alg · Importance sampling, intragroup varianceexpected squared error: 0.121 -> 0.052Improved
Use SDP Alg instead of inverse proportional reweighting on constant valuesSDP Alg · Importance sampling, constant valuesexpected squared error: 0.100 -> 0.051Improved
Use SDP Alg instead of sample mean on spatially-correlated valuesSDP Alg · Snowball sampling, spatially-correlated valuesexpected squared error: 2--4x reductionImproved
Use SDP Alg instead of sample mean on worst-case valuesSDP Alg · Snowball sampling, worst-case valuesexpected squared error: 4--7x reductionImproved
Use SDP Alg instead of mean of most recent w pointsSDP Alg · Selective prediction, worst-case boundexpected squared error: 2--3x reductionImproved

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