Data structure > labels? Unsupervised heuristics for SVM hyperparameter estimation

arXiv:2111.02164v2 Announce Type: replace
Abstract: Classification is one of the main areas of pattern recognition research, and within it, Support Vector Machine (SVM) is one of the most popular methods outside of field of deep learning -- and a de-facto reference for many Machine Learning approaches. Its performance is determined by parameter selection, which is usually achieved by a time-consuming grid search cross-validation procedure (GSCV). That method, however relies on the availability and quality of labelled examples and thus, when …

abstract arxiv classification cs.lg data deep learning heuristics hyperparameter labels machine machine learning pattern recognition performance popular recognition reference research support svm type unsupervised vector