Research map / Learning theory and algorithms / Sample complexity
Which Factorization Machine Modeling Is Better: A Theoretical Answer with Optimal Guarantee
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 |
|---|---|---|---|
| Replace conventional FM's PSD factorization with decoupled factors while retaining zero diagonal | FM · vTEC evaluation average | RMSE: 0.01617 -> 0.01599 | Helped |
| Replace conventional FM's PSD factorization with decoupled factors while retaining zero diagonal | FM · vTEC evaluation average | RTK ratio: 63.10% -> 64.44% | Helped |
| Replace conventional FM with iFM | FM · vTEC TestDay1, TestDay2, TestDay3, TestDay4, TestDay5, TestDay6, TestDay7, TestDay8, TestDay9 | RMSE | Mixed |
| Remove the PSD constraint, allowing negative second-order patterns | FM · Synthetic data with flipped labels and mixed-sign eigenvalues | RMSE | Helped |
| Keep the diagonal-zero constraint while removing the PSD constraint | Generalized FM · Sub-gaussian data | sampling complexity: O(k^{2}d\cdot\mathrm{polylog}(kd)/\tau^{2}) -> O(kd\cdot\mathrm{polylog}(kd)) | Helped |
| Remove the PSD constraint | Conventional FM · Sub-gaussian data | sampling complexity | No clear effect |
Closest papers by meaning
- Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference (NeurIPS 2024 · similarity 0.82)
- Robust Gaussian Processes via Relevance Pursuit (NeurIPS 2024 · similarity 0.81)
- From Generalization Analysis to Optimization Designs for State Space Models (ICML 2024 · similarity 0.81)
- Max Entropy Moment Kalman Filter for Polynomial Systems with Arbitrary Noise (NeurIPS 2025 · similarity 0.81)
- Sparse Gaussian Processes: Structured Approximations and Power-EP Revisited (NeurIPS 2025 · similarity 0.81)
- Variational Linearized Laplace Approximation for Bayesian Deep Learning (ICML 2024 · similarity 0.81)
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.