Reese Pathak

collaborators

7 papers

math.ST2026

Beyond Modern Asymptotics for Log-Likelihood Ratios in Logistic Regression

Hugo Chardon, Reese Pathak, Nikita Zhivotovskiy

We characterize the finite sample behavior of the log-likelihood ratio statistic in binary logistic regression, uniformly over both the design and the target parameter. For $n\geq…

math.MG2026

Optimal mean width and metric entropy estimates for convex bodies

Grigoris Paouris, Reese Pathak

We show that there exists a constant $C > 0$ such that for any $n \geq 1$ and any convex body $K \subset R^{n}$ , \[ 1 \leq \inf_{T \in \mathrm{GL}(n)} \, \frac{M^\ast(TK)}{\…

math.ST2026

Minimum Norm Interpolation via The Local Theory of Banach Spaces: The Role of Gaussianity

Gil Kur, Reese Pathak

We study minimum-norm interpolation (MNI) in overparameterized linear regression with isotropic Gaussian covariates, in settings where the MNI has no closed-form formula. Whereas m…

math.MG2026

On the metric projection onto a convex set: reverse HÃ¶lder inequalities and upper bounds

Reese Pathak

We study the $L^{p} (I^¼)$ -norm of the metric projection onto a closed, convex set $C \subset R^{n}$ when $I^¼$ is the uniform measure on the sphere or the standard Gaussian meas…

math.PR2026

A remark on the majorizing measures theorem for general processes

Reese Pathak, Nikita Zhivotovskiy

We show that the lower bound in the majorizing measures theorem holds for a large class of random vectors. Specifically, suppose $X \sim I^¼$ is a centered random vector in $\mathbf…

math.PR2026

Gaussian Width of Convex Sets via Integral Decompositions, Projections, and the Distribution of Intrinsic Volumes

Reese Pathak, Nikita Zhivotovskiy

We revisit the problem of bounding the expected supremum of a canonical Gaussian process indexed by a convex set $T \subset R^{d}$ . We develop two decompositions for the Gau…