Research map / Adversarial robustness and security / Certified and empirical robustness
How Does Mixup Help With Robustness and Generalization?
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 |
|---|---|---|---|
| Train with Mixup instead of standard empirical risk minimization | Logistic regression and ReLU or max-pooling neural networks · Adversarial robustness | second-order adversarial loss | Helped |
| Use Mixup's data-adaptive regularization instead of standard training | Generalized linear models · Generalization | generalization error bound | Helped |
| Apply Manifold Mixup on the hidden layer | Two-layer ReLU neural networks with squared loss · Generalization | generalization error bound | Helped |
Closest papers by meaning
- Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization (CVPR 2020 · similarity 0.91)
- mixup: Beyond Empirical Risk Minimization (ICLR 2018 · similarity 0.91)
- Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks (ICLR 2020 · similarity 0.90)
- MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps (NeurIPS 2021 · similarity 0.90)
- Over-Training with Mixup May Hurt Generalization (ICLR 2023 · similarity 0.89)
- Adversarial AutoMixup (ICLR 2024 · similarity 0.87)
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.