Research map / Learning theory and algorithms / Sample complexity
Dropout Training is Distributionally Robust Optimal
José Blanchet, Yang Kang, José Luis Montiel Olea, Viet Anh Nguyen, Xuhui Zhang
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 |
|---|---|---|---|
| choose dropout probability delta=c/sqrt(n) with c=z_{1-alpha}*sigma/mu instead of 10-fold cross-validation | dropout training in linear regression · Coverage of population loss, n=1000 | coverage frequency: 0.52 -> 0.88 (alpha=0.1) | Improved |
| choose dropout probability delta=c/sqrt(n) instead of plain OLS | linear regression · Coverage of population loss, n=10000 | coverage frequency: 0.47 -> 0.90 (alpha=0.1) | Improved |
| use unbiased multi-level Monte Carlo estimator instead of standard SGD for dropout training | dropout training in high-dimensional linear regression (d=100, n=50) · parameter divergence from beta*_n, 60 s wall-clock | l2 divergence: outperforms SGD once the number of parallel iterations exceeds ~1000 | Improved |
| increase number of parallelizations L beyond about 2000 for multi-level Monte Carlo (ablation) | unbiased multi-level Monte Carlo dropout · parameter divergence from beta*_n | divergence: saturation after ~2000 parallelizations | No clear effect |
Closest papers by meaning
- On Convergence and Generalization of Dropout Training (NeurIPS 2020 · similarity 0.87)
- Improved Dropout for Shallow and Deep Learning (NeurIPS 2016 · similarity 0.86)
- Dropout Regularization Versus l2-Penalization in the Linear Model (JMLR 2024 · similarity 0.86)
- Stochastic Modified Equations and Dynamics of Dropout Algorithm (ICLR 2024 · similarity 0.86)
- Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization (TPAMI 2021 · similarity 0.86)
- Adversarial Dropout for Supervised and Semi-Supervised Learning (AAAI 2018 · 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.
