Research map / Learning theory and algorithms / Sample complexity
On Achieving Optimal Adversarial Test Error
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 |
|---|---|---|---|
| Choose an appropriate threshold for the convex-loss predictor | Adversarial convex predictors · General data distributions and perturbation sets | Adversarial zero-one risk | Helped |
| Train a shallow ReLU network with early stopping and an optimal adversarial attack | Adversarial training · General data distributions and perturbation sets | Adversarial test error | Helped |
Closest papers by meaning
- Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks (ICML 2020 · similarity 0.90)
- Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization (NeurIPS 2022 · similarity 0.89)
- Expressive Losses for Verified Robustness via Convex Combinations (ICLR 2024 · similarity 0.89)
- Theoretical Analysis of Adversarial Learning: A Minimax Approach (NeurIPS 2019 · similarity 0.88)
- Understanding and Improving Fast Adversarial Training against $l_0$ Bounded Perturbations (NeurIPS 2025 · similarity 0.88)
- Adversarial Training Should Be Cast as a Non-Zero-Sum Game (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.