activity
20032026
most citedA framework to characterize performance of LASSO algorithms

99 citations · 428 across the 78 of their papers we have counts for

collaborators

80 papers

math.PR2026

RDT based upper bounds on the largest average submatrix values

Mihailo Stojnic

We study statistical variants of the classical largest average submatrix problem. For small submatrices (where the dimension is less than linearly proportional to the original matr…

math.PR2026

Proving Lehner's formulas via RDT -- indefinite and asymmetric scenarios

Mihailo Stojnic

The strong asymptotic freeness established in [28,53] allows for the study of norms of Gaussian matrix polynomials via corresponding free operator counterparts. For spectral edges…

math.PR2026

An RDT based confirmation of Lehner's formula for Kronecker-Gaussian matrices

Mihailo Stojnic

Remarkable breakthroughs [25,43] established the so-called strong asymptotic freeness between classical Gaussian random ensembles and their semicircular free counterparts. Along th…

math.ST2026

Precise sample covariance spectral norm error -- an RDT view

Mihailo Stojnic

We study the sample covariance error of centered Gaussians. A remarkable breakthrough [66] established the correct error scaling order and explicitly revealed the critical role of…

math.PR2026

An RDT based approach to large deviations of Wishart and Wigner matrices spectral edges

Mihailo Stojnic

We present a novel methodology for studying \emph{large deviations principles} (LDPs) of random matrices. By utilizing a partially lifted variant of \emph{random duality theory} (R…

cs.LG2026

Ultrametric OGP - parametric RDT \emph{symmetric} binary perceptron connection

Mihailo Stojnic

In [97,99,100], an fl-RDT framework is introduced to characterize \emph{statistical computational gaps} (SCGs). Studying \emph{symmetric binary perceptrons} (SBPs), [100] obtained…