Precise statistical analysis of classification accuracies for adversarial training
From MaRDI portal
Recommendations
- Analysis of classifiers' robustness to adversarial perturbations
- Adversarial robustness for latent models: revisiting the robust-standard accuracies tradeoff
- Robust Classification Under $\ell_0$ Attack for the Gaussian Mixture Model
- The curse of overparametrization in adversarial training: precise analysis of robust generalization for random features regression
- Robustness should not be at odds with accuracy
Cites work
- scientific article; zbMATH DE number 4061904 (Why is no real title available?)
- A modern maximum-likelihood theory for high-dimensional logistic regression
- Adversarial Risk via Optimal Transport and Optimal Couplings
- Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing
- Asymptotic behavior of support vector machine for spiked population model
- Disciplined convex programming
- Does SLOPE outperform bridge regression?
- Fundamental barriers to high-dimensional regression with convex penalties
- High dimensional robust M-estimation: asymptotic variance via approximate message passing
- Information-Theoretically Optimal Compressed Sensing via Spatial Coupling and Approximate Message Passing
- Living on the edge: phase transitions in convex programs with random data
- On the Adversarial Robustness of Robust Estimators
- On the distribution of the largest eigenvalue in principal components analysis
- On the impact of predictor geometry on the performance on high-dimensional ridge-regularized generalized robust regression estimators
- Optimal shrinkage of eigenvalues in the spiked covariance model
- Phase transitions in semidefinite relaxations
- Precise Error Analysis of Regularized <inline-formula> <tex-math notation="LaTeX">$M$ </tex-math> </inline-formula>-Estimators in High Dimensions
- Reconciling modern machine-learning practice and the classical bias-variance trade-off
- Sharp Time–Data Tradeoffs for Linear Inverse Problems
- Sparse PCA via covariance thresholding
- Surprises in high-dimensional ridgeless least squares interpolation
- The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
- The LASSO Risk for Gaussian Matrices
- The Noise-Sensitivity Phase Transition in Compressed Sensing
- The distribution of the Lasso: uniform control over sparse balls and adaptive parameter tuning
- The phase transition for the existence of the maximum likelihood estimate in high-dimensional logistic regression
Cited in
(9)- Adversarial robustness for latent models: revisiting the robust-standard accuracies tradeoff
- Robustness should not be at odds with accuracy
- The geometry of adversarial training in binary classification
- Sharp global convergence guarantees for iterative nonconvex optimization with random data
- Analysis of classifiers' robustness to adversarial perturbations
- Improving the accuracy-robustness trade-off of classifiers via adaptive smoothing
- Nonasymptotic bounds for adversarial excess risk under misspecified models
- Precise Statistical Analysis of Classification Accuracies for Adversarial Training
- The curse of overparametrization in adversarial training: precise analysis of robust generalization for random features regression
This page was built for publication: Precise statistical analysis of classification accuracies for adversarial training
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2091832)
