Cheng Soon Ong

Monge blunts Bayes: Hardness Results for Adversarial Training

2018 · arXiv (Cornell University)

The last few years have seen a staggering number of empirical studies of the robustness of neural networks in a model of adversarial perturbations of their inputs. Most rely on an adversary which carries out …

Probabilistic Knowledge Graph Construction: Compositional and Incremental Approaches

2016 · arXiv (Cornell University)

Knowledge graph construction consists of two tasks: extracting information from external resources (knowledge population) and inferring missing information through a statistical analysis on the extracted information (knowledge completion). In many cases, insufficient external resources in …

Exact, Fast and Expressive Poisson Point Processes via Squared Neural Families

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

We introduce squared neural Poisson point processes (SNEPPPs) by parameterising the intensity function by the squared norm of a two layer neural network. When the hidden layer is fixed and the second layer has a …