One-Bit Quantization and Sparsification for Multiclass Linear Classification via Regularized Regression

arXiv:2402.10474v1 Announce Type: new
Abstract: We study the use of linear regression for multiclass classification in the over-parametrized regime where some of the training data is mislabeled. In such scenarios it is necessary to add an explicit regularization term, $\lambda f(w)$, for some convex function $f(\cdot)$, to avoid overfitting the mislabeled data. In our analysis, we assume that the data is sampled from a Gaussian Mixture Model with equal class sizes, and that a proportion $c$ of the training labels …

abstract arxiv classification cs.lg data function lambda linear linear regression overfitting quantization regression regularization stat.ml study training training data type via