AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Partitioned Sampling of Public Opinions Based on Their Social Dynamics

Weiran Huang, Liang Li, Wei Chen

AAAI 2017 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 5 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 greedy partitioned sampling instead of naive samplingWeibo polling with λ_i=1 · Weibo, λ_i=1; target E_M[Var_S( f̂)] = 3.86e-5samples: 8000 -> 4794; saving 40.1%Improved
Use greedy partitioned sampling instead of naive samplingWeibo polling with tweet-count updating rates · Weibo, λ_i set to tweet counts; target E_M[Var_S( f̂)] = 3.86e-5samples: 8000 -> 4885; saving 38.9%Improved
Use missing and perturbed similarities rather than exact similarities (ablation)Greedy partitioning on Weibo · Weibo, λ_i=1 and tweet-count updating-rate settingsexpected sample varianceNo clear effect
Increase the planted-graph ratio p_H/p_LGreedy partitioned sampling · Large synthetic graphimprovement in expected sample variance: 10^3 -> 10^5Improved
Increase inward probabilitiesGreedy partitioned sampling · Synthetic graphsimprovement in expected sample varianceHurt
Increase sample sizeSDP partitioned sampling · Small synthetic graphsampling qualityHurt
Use greedy partitioning rather than SDP partitioningPartitioned sampling · Small synthetic graphsampling qualityMixed

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