AdaBoost and robust one-bit compressed sensing
Summary: This paper studies binary classification in robust one-bit compressed sensing with adversarial errors. It is assumed that the model is overparametrized and that the parameter of interest is effectively sparse. AdaBoost is considered, and, through its relation to the max \(\ell_1\)-matrix-classifier rediction error bounds are derived. The developed theory is general and allows for heavy-tailed feature distributions, requiring only a weak moment assumption and an anti-concentration condition. Improved convergence rates are shown when the features satisfy a small deviation lower bound. In particular, the results provide an explanation why interpolating adversarial noise can be harmless for classification problems. Simulations illustrate the presented theory.
- Robust one-bit compressed sensing with partial circulant matrices
- Random classification noise defeats all convex potential boosters
- Boosting in the presence of outliers: adaptive classification with nonconvex loss functions
- An approach to one-bit compressed sensing based on probably approximately correct learning theory
- Robust 1-bit compressed sensing via hinge loss minimization
- A decision-theoretic generalization of on-line learning and an application to boosting
- A model of double descent for high-dimensional binary linear classification
- A precise high-dimensional asymptotic theory for boosting and minimum-\(\ell_1\)-norm interpolated classifiers
- Adaptive estimation of a quadratic functional by model selection.
- Additive logistic regression: a statistical view of boosting. (With discussion and a rejoinder by the authors)
- Arcing classifiers. (With discussion)
- Atomic Decomposition by Basis Pursuit
- Benign overfitting in linear regression
- Boosting as a regularized path to a maximum margin classifier
- Boosting for high-dimensional linear models
- Boosting the margin: a new explanation for the effectiveness of voting methods
- Boosting with early stopping: convergence and consistency
- Empirical margin distributions and bounding the generalization error of combined classifiers
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 7626737 (Why is no real title available?)
- scientific article; zbMATH DE number 6781369 (Why is no real title available?)
- Improved boosting algorithms using confidence-rated predictions
- Inequalities of Bernstein-Jackson-type and the degree of compactness of operators in Banach spaces
- Learning without concentration
- Mathematical foundations of infinite-dimensional statistical models
- Moment inequalities for sums of dependent random variables under projective conditions
- Non-Gaussian hyperplane tessellations and robust one-bit compressed sensing
- Normal Approximation by Stein’s Method
- On sparse reconstruction from Fourier and Gaussian measurements
- On the Bayes-risk consistency of regularized boosting methods.
- On the minimum of several random variables
- On the robustness of minimum norm interpolators and regularized empirical risk minimizers
- One-bit compressed sensing by linear programming
- One-bit compressed sensing with non-Gaussian measurements
- One-bit compressive sensing of dictionary-sparse signals
- One-Bit Compressive Sensing With Norm Estimation
- Population theory for boosting ensembles.
- Process consistency for AdaBoost.
- Reconciling modern machine-learning practice and the classical bias-variance trade-off
- Reconstruction and subgaussian operators in asymptotic geometric analysis
- Robust 1-bit Compressed Sensing and Sparse Logistic Regression: A Convex Programming Approach
- Robust 1-Bit Compressive Sensing via Binary Stable Embeddings of Sparse Vectors
- Soft margins for AdaBoost
- Stability and instance optimality for Gaussian measurements in compressed sensing
- Surprises in high-dimensional ridgeless least squares interpolation
- The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
- The implicit bias of gradient descent on separable data
- The Integral of a Symmetric Unimodal Function over a Symmetric Convex Set and Some Probability Inequalities
- The rate of convergence of AdaBoost
This page was built for publication: AdaBoost and robust one-bit compressed sensing
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2102435)
