3 papers
cs.LG2026
Optimal Dimension-Free Sampling for Regularized Classification
Meysam Alishahi, Alexander Munteanu, Simon Omlor +1
We prove optimal sampling bounds achieving -relative error for a broad class of Lipschitz continuous classification loss functions under various regularization t…
cs.LG2026
TabKDE: Simple and Scalable Tabular Data Generation with Kernel Density Estimates
Meysam Alishahi, Yan Zheng, Junpeng Wang +2
Tabular data generation considers a large table with multiple columns -- each column comprised of numerical, categorical, or sometimes ordinal values. The goal is to produce new ro…
math.CO2025
The Matching Ramsey Number of Hypergraphs, Revisited
Saeed Shaebani, Meysam Alishahi
Suppose that a hypergraph and an arbitrary nonempty (finite or infinite) set of available colors are given. Each color is associated with a frequency , wh…