2 citations · 2 across the 5 of their papers we have counts for
6 papers
Coreset Spectral Clustering
Ben Jourdan, Gregory Schwartzman, Peter Macgregor +1
Coresets have become an invaluable tool for solving -means and kernel -means clustering problems on large datasets with small numbers of clusters. On the other hand, spectral…
Mini-Batch Kernel -means
Ben Jourdan, Gregory Schwartzman
We present the first mini-batch kernel -means algorithm, offering an order of magnitude improvement in running time compared to the full batch algorithm. A single iteration of o…
Stochastic Distance in Property Testing
Uri Meir, Gregory Schwartzman, Yuichi Yoshida
We introduce a novel concept termed "stochastic distance" for property testing. Diverging from the traditional definition of distance, where a distance implies that there exist…
Exfiltration of personal information from ChatGPT via prompt injection
Gregory Schwartzman
We report that ChatGPT 4 and 4o are susceptible to a prompt injection attack that allows an attacker to exfiltrate users' personal data. It is applicable without the use of any 3rd…
Mini-batch Submodular Maximization
Gregory Schwartzman
We present the first mini-batch algorithm for maximizing a non-negative monotone decomposable submodular function, , under a set of constraints. We consider two…
Local Max-Cut on Sparse Graphs
Gregory Schwartzman
We bound the smoothed running time of the FLIP algorithm for local Max-Cut as a function of , the arboricity of the input graph. We show that, with high probability and in expec…