Alert button
Picture for Hayden Helm

Hayden Helm

Alert button

A Statistical Turing Test for Generative Models

Sep 16, 2023
Hayden Helm, Carey E. Priebe, Weiwei Yang

Figure 1 for A Statistical Turing Test for Generative Models
Figure 2 for A Statistical Turing Test for Generative Models

The emergence of human-like abilities of AI systems for content generation in domains such as text, audio, and vision has prompted the development of classifiers to determine whether content originated from a human or a machine. Implicit in these efforts is an assumption that the generation properties of a human are different from that of the machine. In this work, we provide a framework in the language of statistical pattern recognition that quantifies the difference between the distributions of human and machine-generated content conditioned on an evaluation context. We describe current methods in the context of the framework and demonstrate how to use the framework to evaluate the progression of generative models towards human-like capabilities, among many axes of analysis.

Viaarxiv icon

Vertex Classification on Weighted Networks

Jun 07, 2019
Hayden Helm, Joshua Vogelstein, Carey Priebe

Figure 1 for Vertex Classification on Weighted Networks
Figure 2 for Vertex Classification on Weighted Networks
Figure 3 for Vertex Classification on Weighted Networks
Figure 4 for Vertex Classification on Weighted Networks

This paper proposes a discrimination technique for vertices in a weighted network. We assume that the edge weights and adjacencies in the network are conditionally independent and that both sources of information encode class membership information. In particular, we introduce a edge weight distribution matrix to the standard K-Block Stochastic Block Model to model weighted networks. This allows us to develop simple yet powerful extensions of classification techniques using the spectral embedding of the unweighted adjacency matrix. We consider two assumptions on the edge weight distributions and propose classification procedures in both settings. We show the effectiveness of the proposed classifiers by comparing them to quadratic discriminant analysis following the spectral embedding of a transformed weighted network. Moreover, we discuss and show how the methods perform when the edge weights do not encode class membership information.

* 11 pages 
Viaarxiv icon