Research map / Learning theory and algorithms / Prediction and decision losses
Significance Tests for Neural Networks
Enguerrand Horel, Kay Giesecke
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 NN test instead of t-test on a misspecified linear model | significance test · Synthetic, relevant variables X1-X6 | power at 5% level: 0.07 -> 1 | Improved |
| use discretization method instead of series method for asymptotic distribution (ablation) | NN significance test · Synthetic, irrelevant variable X8 | size at 5% level: 0.35 -> 0 | Improved |
| add correlation among features via Gaussian copula (ablation) | NN test (discretization) · Synthetic, irrelevant variable X8 | size at 5% level: 0 -> 0.004 | No clear effect |
| use neural network instead of linear model | regression fit · Synthetic regression | test MSE: 0.35 -> 3.1 | Improved |
Closest papers by meaning
- Full Bayesian Significance Testing for Neural Networks (AAAI 2024 · similarity 0.84)
- Permutation-Based Hypothesis Testing for Neural Networks (AAAI 2024 · similarity 0.83)
- On the Variance of Neural Network Training with respect to Test Sets and Distributions (ICLR 2024 · similarity 0.82)
- A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks (ICML 2024 · similarity 0.80)
- Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model (ICLR 2025 · similarity 0.80)
- Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data (NeurIPS 2025 · 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.
