22 citations · 78 across the 23 of their papers we have counts for
5 papers · 2 filters
A complexity analysis of statistical learning algorithms
Mark A. Kon
We apply information-based complexity analysis to support vector machine (SVM) algorithms, with the goal of a comprehensive continuous algorithmic analysis of such algorithms. This…
On the probabilistic continuous complexity conjecture
Mark A. Kon
In this paper we prove the probabilistic continuous complexity conjecture. In continuous complexity theory, this states that the complexity of solving a continuous problem with pro…
On Some Integrated Approaches to Inference
Mark A. Kon, Leszek Plaskota
We present arguments for the formulation of unified approach to different standard continuous inference methods from partial information. It is claimed that an explicit partition o…
Feature vector regularization in machine learning
Yue Fan, Louise Raphael, Mark Kon
Problems in machine learning (ML) can involve noisy input data, and ML classification methods have reached limiting accuracies when based on standard ML data sets consisting of fea…
Empirical Normalization for Quadratic Discriminant Analysis and Classifying Cancer Subtypes
Mark A. Kon, Nikolay Nikolaev
We introduce a new discriminant analysis method (Empirical Discriminant Analysis or EDA) for binary classification in machine learning. Given a dataset of feature vectors, this met…