Research map / Learning theory and algorithms / Matrix and tensor methods
Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| use weighted rank-one PGD skill estimation instead of majority voting | weighted-majority label aggregation · Web | prediction error: 0.2693 -> 0.1485 | Helped |
| use PGD instead of majority voting | label aggregation · RTE1 | prediction error: 0.1031 -> 0.07 | Helped |
| use PGD instead of Opt-D&S | label aggregation · Dogs | prediction error: 0.1689 -> 0.1660 | Helped |
| use PGD instead of ER | label aggregation · Temp | prediction error: 0.052 -> 0.0512 | Helped |
| use PGD instead of KOS | label aggregation · RTE1 | prediction error: 0.3975 -> 0.07 | Helped |
| use PGD instead of Opt-D&S on sparse ring graph | label aggregation · Synthetic ring graph | prediction error | Helped |
| increase number of tasks | PGD · Synthetic graphs (clique, star, ring) | average prediction error | Helped |
| sparsify worker interaction graph (lower maximum degree) | PGD · RTE1 and Temp | average prediction error | Hurt |
Closest papers by meaning
- Adversarial Crowdsourcing Through Robust Rank-One Matrix Completion (NeurIPS 2020 · similarity 0.89)
- Exact Exponent in Optimal Rates for Crowdsourcing (ICML 2016 · similarity 0.87)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.86)
- Crowdsourcing via Annotator Co-occurrence Imputation and Provable Symmetric Nonnegative Matrix Factorization (ICML 2021 · similarity 0.86)
- In-depth Analysis of Low-rank Matrix Factorisation in a Federated Setting (AAAI 2025 · similarity 0.84)
- Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting (NeurIPS 2024 · similarity 0.84)
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.