Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Soft Tensor Regression
Georgia Papadogeorgou, Zhengwu Zhang, David B. Dunson
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 |
|---|---|---|---|
| add softening of PARAFAC (Softer instead of hard PARAFAC, D=3) (ablation) | hard PARAFAC · Simulation 32x32 squares | predictive MSE: 8.99 -> 5.05 | Improved |
| add softening of PARAFAC (Softer instead of hard PARAFAC, D=3) (ablation) | hard PARAFAC · Simulation 32x32 feet | predictive MSE: 41.8 -> 31.9 | Improved |
| add softening of PARAFAC (Softer instead of hard PARAFAC, D=3) (ablation) | hard PARAFAC · Simulation 32x32 dog | predictive MSE: 45.4 -> 35.0 | Improved |
| add softening of PARAFAC (Softer instead of hard PARAFAC, D=3) (ablation) | hard PARAFAC · Simulation 32x32 diagonal | predictive MSE: 29.7 -> 1.41 | Improved |
| use Softer instead of Lasso | Lasso · Simulation 32x32 diagonal | predictive MSE: 0.81 -> 1.41 | Hurt |
| add softening of PARAFAC (ablation) | hard PARAFAC · Simulation 32x32 diagonal | sensitivity: 3 -> 100 | Improved |
| add softening of PARAFAC (ablation) | hard PARAFAC · Simulation 32x32 dog | false positive rate: 12.4 -> 5.2 | Improved |
| add softening of PARAFAC (ablation) | hard PARAFAC · Simulation 32x32 squares | rMSE non-zero entries: 0.148 -> 0.11 | Improved |
| add softening of PARAFAC (ablation) | hard PARAFAC · Simulation 20x20 true rank 3 | performance | No clear effect |
| use smaller sample size n=200 (ablation) | Softer · Simulation, n=200 | closeness to hard PARAFAC | Mixed |
| add softening of PARAFAC (ablation) | hard PARAFAC · HCP brain connectomics, continuous outcomes | prediction | No clear effect |
| use Softer instead of Lasso | Lasso · HCP Depressive Ep | accuracy: over 90% | Improved |
Closest papers by meaning
- Factor Augmented Tensor-on-Tensor Neural Networks (AAAI 2025 · similarity 0.90)
- Bayesian Tensor Regression (JMLR 2017 · similarity 0.89)
- High-Dimensional Tensor Regression With Oracle Properties (ICML 2025 · similarity 0.89)
- Tensor Graphical Model: Non-Convex Optimization and Statistical Inference (TPAMI 2019 · similarity 0.88)
- Low-Rank Tensor Transitions (LoRT) for Transferable Tensor Regression (ICML 2025 · similarity 0.87)
- Identification of Latent Confounders via Investigating the Tensor Ranks of the Nonlinear Observations (ICML 2025 · similarity 0.86)
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.
