Research map / Probabilistic and scientific modeling / Variational and generative sampling
An Efficient Joint Learning Approach for Item Response Theory
Tanish Agarwal, Kaustubh Shivshankar Shejole, Arpit Agarwal
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use Polya-Gamma EM joint estimation (PGEM) instead of Spectral | Rasch model · ICAR-SAPA | AUC: 0.804 -> 0.814 | Improved |
| PGEM instead of Spectral | Rasch model · ICAR-SAPA | runtime (s): 2128.68 -> 52.71 | Improved |
| PGEM instead of JMLE | Rasch model · BOOK-GENOME | AUC: 0.657 -> 0.698 | Improved |
| PGEM instead of MMLE | Rasch model · BOOK-GENOME | runtime: 1509.21 per prior vs 8318.86 | Mixed |
| PGEM instead of CMLE | Rasch model · ML-100K | AUC: 0.475 -> 0.739 | Improved |
| PGEM instead of JMLE/Spectral in sparse regimes | Rasch model · Synthetic, varying sparsity | normalized l2 error | Improved |
| PGEM instead of Spectral and CMLE as density decreases | Rasch model · Synthetic, varying density | accuracy and runtime | Improved |
| PGEM on filtered denser datasets | Rasch model · Filtered datasets (Table 12) | predictive metrics | Improved |
Closest papers by meaning
- A Spectral Approach to Item Response Theory (NeurIPS 2022 · similarity 0.92)
- Can We Trust Item Response Theory for AI Evaluation? (NeurIPS 2026 · similarity 0.85)
- Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation (ICML 2026 · similarity 0.83)
- Novel Spectral Algorithms for the Partial Credit Model (ICML 2024 · similarity 0.82)
- Neighborhood-Aware Negative Sampling for Student Knowledge and Behavior Modeling (AAAI 2025 · similarity 0.81)
- Active preference learning for ordering items in- and out-of-sample (NeurIPS 2024 · similarity 0.80)
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.
