29 citations · 41 across the 4 of their papers we have counts for
6 papers
Differentially private partition selection
Damien Desfontaines, James Voss, Bryant Gipson +1
Many data analysis operations can be expressed as a GROUP BY query on an unbounded set of partitions, followed by a per-partition aggregation. To make such a query differentially p…
A Pseudo-Euclidean Iteration for Optimal Recovery in Noisy ICA
James Voss, Mikhail Belkin, Luis Rademacher
Independent Component Analysis (ICA) is a popular model for blind signal separation. The ICA model assumes that a number of independent source signals are linearly mixed to form th…
Eigenvectors of Orthogonally Decomposable Functions
Mikhail Belkin, Luis Rademacher, James Voss
The Eigendecomposition of quadratic forms (symmetric matrices) guaranteed by the spectral theorem is a foundational result in applied mathematics. Motivated by a shared structure f…
The Hidden Convexity of Spectral Clustering
James Voss, Mikhail Belkin, Luis Rademacher
In recent years, spectral clustering has become a standard method for data analysis used in a broad range of applications. In this paper we propose a new class of algorithms for mu…
The More, the Merrier: the Blessing of Dimensionality for Learning Large Gaussian Mixtures
Joseph Anderson, Mikhail Belkin, Navin Goyal +2
In this paper we show that very large mixtures of Gaussians are efficiently learnable in high dimension. More precisely, we prove that a mixture with known identical covariance mat…
Blind Signal Separation in the Presence of Gaussian Noise
Mikhail Belkin, Luis Rademacher, James Voss
A prototypical blind signal separation problem is the so-called cocktail party problem, with n people talking simultaneously and n different microphones within a room. The goal is…