7 papers
Topological Equivalence of Spectral and Density Cluster Hierarchies
Sajjad Hashemian
We compare two canonical ways to recover hierarchical clustering from an underlying density : the \emph{density cluster tree} given by connected components of superlevel sets $\…
Hierarchical Fourier Approximation for Variational Quantum Distribution Learning
Taha Hoseinpour Asli, Sajjad Hashemian, Ebrahim Ardeshir-Larijani
We study variational quantum distribution learning through a hierarchy of Walsh--Fourier approximations on the Boolean cube. At each level, a selected set of target Fourier coeffic…
Quantum Sketches, Hashing, and Approximate Nearest Neighbors
Sajjad Hashemian
Motivated by Johnson--Lindenstrauss dimension reduction, amplitude encoding, and the view of measurements as hash-like primitives, one might hope to compress an -point approxima…
List-Decodable Regression via Expander Sketching
Herbod Pourali, Sajjad Hashemian, Ebrahim Ardeshir-Larijani
We introduce an expander-sketching framework for list-decodable linear regression that achieves sample complexity , list size , and near input-s…
Efficient and Accurate Estimation of Lipschitz Constants for Hybrid Quantum-Classical Decision Models
Sajjad Hashemian, Mohammad Saeed Arvenaghi
In this paper, we propose a novel framework for efficiently and accurately estimating Lipschitz constants in hybrid quantum-classical decision models. Our approach integrates class…
Almost Linear Time Consistent Mode Estimation and Quick Shift Clustering
Sajjad Hashemian
In this paper, we propose a method for density-based clustering in high-dimensional spaces that combines Locality-Sensitive Hashing (LSH) with the Quick Shift algorithm. The Quick…
Optimal Bound for PCA with Outliers using Higher-Degree Voronoi Diagrams
Sajjad Hashemian, Mohammad Saeed Arvenaghi, Ebrahim Ardeshir-Larijani
In this paper, we introduce new algorithms for Principal Component Analysis (PCA) with outliers. Utilizing techniques from computational geometry, specifically higher-degree Vorono…