Oren Mangoubi

collaborators

4 papers

cs.LG2025

Efficient Diffusion Models for Symmetric Manifolds

Oren Mangoubi, Neil He, Nisheeth K. Vishnoi

We introduce a framework for designing efficient diffusion models for $d$ -dimensional symmetric-space Riemannian manifolds, including the torus, sphere, special orthogonal group an…

cs.DS2025

Private Low-Rank Approximation for Covariance Matrices, Dyson Brownian Motion, and Eigenvalue-Gap Bounds for Gaussian Perturbations

Oren Mangoubi, Nisheeth K. Vishnoi

We consider the problem of approximating a $d \times d$ covariance matrix $M$ with a rank- $k$ matrix under $(ε, I^´)$ -differential privacy. We present and analyze a complex…

cs.DS2024

Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers

Oren Mangoubi, Nisheeth K. Vishnoi

We consider the problem of sampling from a log-concave distribution $I ¨ (I^¸) \propto e^{- f (I^¸)}$ constrained to a polytope $K := {I^¸ \in R^{d} : A I^¸ \leq b}$ , where $A\in \mathb…

math.ST2024

Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions

Peiyao Lai, Oren Mangoubi

Given a matrix $A \in R^{m \times d}$ with singular values $I ¨ _{1} \geq \dots \geq I ¨ _{d}$ , and a random matrix $G \in R^{m \times d}$ with iid $N (0, T)$ entries for som…