3 papers
cs.DS2021
On the Geometry of Stable Steiner Tree Instances
James Freitag, Neshat Mohammadi, Aditya Potukuchi +1
In this note we consider the Steiner tree problem under Bilu-Linial stability. We give strong geometric structural properties that need to be satisfied by stable instances. We then…
cs.LG2019
Robust Mahalanobis Metric Learning via Geometric Approximation Algorithms
Diego Ihara, Neshat Mohammadi, Francesco Sgherzi +1
Learning Mahalanobis metric spaces is an important problem that has found numerous applications. Several algorithms have been designed for this problem, including Information Theor…
cs.CG2018
Algorithms for metric learning via contrastive embeddings
Diego Ihara Centurion, Neshat Mohammadi, Anastasios Sidiropoulos
We study the problem of supervised learning a metric space under discriminative constraints. Given a universe and sets of similar and…