works on

From the 1 of 24 linked papers with an AI index.

activity
20242026
collaborators
Showing 2025Show all

6 papers · 1 filter

math.PR2025

Universal entrywise eigenvector fluctuations in delocalized spiked matrix models and asymptotics of rounded spectral algorithms

Shujing Chen, Dmitriy Kunisky

We consider the distribution of the top eigenvector of a spiked matrix model of the form , in the supercritical regime where has an outlier eigenva…

stat.ML2025

Nonlinear Laplacians: Tunable principal component analysis under directional prior information

Yuxin Ma, Dmitriy Kunisky

We introduce a new family of algorithms for detecting and estimating a rank-one signal from a noisy observation under prior information about that signal's direction, focusing on e…

math.ST2025

Computational and statistical lower bounds for low-rank estimation under general inhomogeneous noise

Debsurya De, Dmitriy Kunisky

Recent work has generalized several results concerning the well-understood spiked Wigner matrix model of a low-rank signal matrix corrupted by additive i.i.d. Gaussian noise to the…

math.PR2025

Asymptotic Bounds and Online Algorithms for Average-Case Matrix Discrepancy

Dmitriy Kunisky, Timm Oertel, Nicola Wengiel +1

We study the matrix discrepancy problem in the average-case setting. Given a sequence of symmetric matrices , its discrepancy is defined as the minimal…

math.CO2025

The Lovász number of random circulant graphs

Afonso S. Bandeira, Jarosław Błasiok, Daniil Dmitriev +3

This paper addresses the behavior of the Lovász number for dense random circulant graphs. The Lovász number is a well-known semidefinite programming upper bound on the independen…

math.FA2025

On the Structure of Bad Science Matrices

Alex Albors, Hisham Bhatti, Lukshya Ganjoo +5

The bad science matrix problem consists in finding, among all matrices with rows having unit norm, one that maximizes $β(A) = \frac{1}{2^n…