25 citations · 44 across the 12 of their papers we have counts for
13 papers
Recovery Theory for Projected Power Iterations in Permutation Synchronization
Vahan Huroyan, Gilad Lerman
We study the projected power method (PPM) for synchronizing \(n\) unknown permutations of \(m\) objects under a possibly sparse uniform corruption model. Each pair is observed with…
3DMPE: 3D Multi-Perspective Embedding
Vahan Huroyan, Md Rahat-uz-Zaman, Stephen Kobourov
We study 3D point cloud reconstruction from multiple partially observed 2D projections. Given two or more projections of an unknown 3D point cloud, together with cross-view point c…
Do Satellite Tasks Need Special Pretraining?
Ani Vanyan, Alvard Barseghyan, Hakob Tamazyan +4
Foundation models have advanced machine learning across various modalities, including images. Recently multiple teams trained foundation models specialized for remote sensing appli…
Analyzing Local Representations of Self-supervised Vision Transformers
Ani Vanyan, Alvard Barseghyan, Hakob Tamazyan +3
In this paper, we present a comparative analysis of various self-supervised Vision Transformers (ViTs), focusing on their local representative power. Inspired by large language mod…
Balancing between the Local and Global Structures (LGS) in Graph Embedding
Jacob Miller, Vahan Huroyan, Stephen Kobourov
We present a method for balancing between the Local and Global Structures (LGS) in graph embedding, via a tunable parameter. Some embedding methods aim to capture global structures…
Spherical Graph Drawing by Multi-dimensional Scaling
Jacob Miller, Vahan Huroyan, Stephen Kobourov
We describe an efficient and scalable spherical graph embedding method. The method uses a generalization of the Euclidean stress function for Multi-Dimensional Scaling adapted to s…
Browser-based Hyperbolic Visualization of Graphs
Jacob Miller, Stephen Kobourov, Vahan Huroyan
Hyperbolic geometry offers a natural focus + context for data visualization and has been shown to underlie real-world complex networks. However, current hyperbolic network visualiz…
ENS-t-SNE: Embedding Neighborhoods Simultaneously t-SNE
Jacob Miller, Vahan Huroyan, Raymundo Navarrete +2
When visualizing a high-dimensional dataset, dimension reduction techniques are commonly employed which provide a single 2-dimensional view of the data. We describe ENS-t-SNE: an a…
On Random Graph Properties
Hang Chen, Vahan Huroyan, Stephen Kobourov +1
We consider 15 properties of labeled random graphs that are of interest in the graph-theoretical and the graph mining literature, such as clustering coefficients, centrality measur…
Same Stats, Different Graphs: Exploring the Space of Graphs in Terms of Graph Properties
Hang Chen, Vahan Huroyan, Utkarsh Soni +3
Data analysts commonly utilize statistics to summarize large datasets. While it is often sufficient to explore only the summary statistics of a dataset (e.g., min/mean/max), Anscom…
Multi-Perspective, Simultaneous Embedding
Md Iqbal Hossain, Vahan Huroyan, Stephen Kobourov +1
We describe MPSE: a Multi-Perspective Simultaneous Embedding method for visualizing high-dimensional data, based on multiple pairwise distances between the data points. Specificall…
Solving Jigsaw Puzzles By the Graph Connection Laplacian
Vahan Huroyan, Gilad Lerman, Hau-Tieng Wu
We propose a novel mathematical framework to address the problem of automatically solving large jigsaw puzzles. This problem assumes a large image, which is cut into equal square p…
Distributed Robust Subspace Recovery
Vahan Huroyan, Gilad Lerman
We propose distributed solutions to the problem of Robust Subspace Recovery (RSR). Our setting assumes a huge dataset in an ad hoc network without a central processor, where each n…