Boosting Randomized Smoothing with Variance Reduced Classifiers.
Miklós Z. HorváthMark Niklas MüllerMarc FischerMartin T. VechevPublished in: CoRR (2021)
Keyphrases
- ensemble learning
- randomized trees
- weak classifiers
- weak learners
- decision stumps
- feature selection
- boosting algorithms
- improving classification accuracy
- ensemble classifier
- bias variance decomposition
- boosting framework
- decision forest
- variance reduction
- training data
- majority voting
- naive bayes
- multiple classifier systems
- accurate classifiers
- support vector
- adaboost algorithm
- strong classifier
- boosted classifiers
- ensemble classification
- linear classifiers
- classification models
- multiclass classification
- combining classifiers
- classification systems
- training samples
- weighted voting
- ensemble methods
- learning algorithm
- low variance
- discriminative classifiers
- classifier combination
- training set
- binary classification problems
- supervised learning
- covariance matrix
- classifier ensemble
- base learners
- classification accuracy
- object detectors
- base classifiers
- classification algorithm
- loss function