Uri Itai

Nira Dyn, Uri Itai, Nir Sharon

Given a set of matrices, modeled as samples of a matrix-valued function, we suggest a method to approximate the underline function using a product approximation operator. This operator extends known approximation methods by exploiting the structure of the matrices in the samples set, and based on decomposition theorems. We introduce our approach in detail and discuss its advantages using a few examples. In addition, we provide basic tools for analyzing properties of the matrix functions generated by our approximation operators.

Natan Katz, Uri Itai

The goodness of fit methods for classification problems relies traditionally on confusion matrices. This paper aims to enrich these methods with a risk evaluation and stability analysis tools. For this purpose, we present a parametric PDF framework.

Uri Itai, Natan Katz

The multi-class prediction had gained popularity over recent years. Thus measuring fit goodness becomes a cardinal question that researchers often have to deal with. Several metrics are commonly used for this task. However, when one has to decide about the right measurement, he must consider that different use-cases impose different constraints that govern this decision. A leading constraint at least in \emph{real world} multi-class problems is imbalanced data: Multi categorical problems hardly provide symmetrical data. Hence, when we observe common KPIs (key performance indicators), e.g., Precision-Sensitivity or Accuracy, one can seldom interpret the obtained numbers into the model's actual needs. We suggest generalizing Matthew's correlation coefficient into multi-dimensions. This generalization is based on a geometrical interpretation of the generalized confusion matrix.

Uri Itai, Asael Bar Ilan, Teddy Lazebnik

Detecting out-of-distribution (OOD) data is a critical task for maintaining model reliability and robustness. In this study, we propose a novel anomaly detection algorithm that leverages the convex hull (CH) property of a dataset by exploiting the observation that OOD samples marginally increase the CH's volume compared to in-distribution samples. Thus, we establish a decision boundary between OOD and in-distribution data by iteratively computing the CH's volume as samples are removed, stopping when such removal does not significantly alter the CH's volume. The proposed algorithm is evaluated against seven widely used anomaly detection methods across ten datasets, demonstrating performance comparable to state-of-the-art (SOTA) techniques. Furthermore, we introduce a computationally efficient criterion for identifying datasets where the proposed method outperforms existing SOTA approaches.