Výsledky vyhledávání - "Bratincsák, Andras"

Report

Out-of-Distribution Detection using Maximum Entropy Coding

Autor: Abolfazli, Mojtaba, Amirani, Mohammad Zaeri, Høst-Madsen, Anders, Zhang, June, Bratincsak, Andras

Given a default distribution $P$ and a set of test data $x^M=\{x_1,x_2,\ldots,x_M\}$ this paper seeks to answer the question if it was likely that $x^M$ was generated by $P$. For discrete distributions, the definitive answer is in principle given by

Externí odkaz: http://arxiv.org/abs/2404.17023

Zobrazit plný text záznamu

Report

Out-of-Distribution Detection using BiGAN and MDL

Autor: Abolfazli, Mojtaba, Arimani, Mohammad Zaeri, Host-Madsen, Anders, Zhang, June, Bratincsak, Andras

We consider the following problem: we have a large dataset of normal data available. We are now given a new, possibly quite small, set of data, and we are to decide if these are normal data, or if they are indicating a new phenomenon. This is a novel

Externí odkaz: http://arxiv.org/abs/2206.01851

Zobrazit plný text záznamu

Report

Graph Compression with Application to Model Selection

Autor: Abolfazli, Mojtaba, Host-Madsen, Anders, Zhang, June, Bratincsak, Andras

Many multivariate data such as social and biological data exhibit complex dependencies that are best characterized by graphs. Unlike sequential data, graphs are, in general, unordered structures. This means we can no longer use classic, sequential-ba

Externí odkaz: http://arxiv.org/abs/2110.00701

Zobrazit plný text záznamu

Report

Graph Coding for Model Selection and Anomaly Detection in Gaussian Graphical Models

Autor: Abolfazli, Mojtaba, Host-Madsen, Anders, Zhang, June, Bratincsak, Andras

A classic application of description length is for model selection with the minimum description length (MDL) principle. The focus of this paper is to extend description length for data analysis beyond simple model selection and sequences of scalars.

Externí odkaz: http://arxiv.org/abs/2102.02431

Zobrazit plný text záznamu