Samuel B. Hopkins

activity

20232026

collaborators

4 papers

cs.DS2026

Algorithms with Polynomially-Improved Approximation Factors for the $2 \to q$ Norm, and Applications

Samuel B. Hopkins, Stefan Tiegel

The $2 \to q$ norm of a matrix $X \in R^{n \times d}$ is defined as $∥ X ∥_{2 \to q} = sup_{∥ v ∥_{2} = 1} ∥ X v ∥_{q}$ . We give…

cs.DS2024

SoS Certificates for Sparse Singular Values and Their Applications: Robust Statistics, Subspace Distortion, and More

Ilias Diakonikolas, Samuel B. Hopkins, Ankit Pensia +1

We study $sparse singular value certificates$ for random rectangular matrices. If $M$ is an $n \times d$ matrix with independent Gaussian entries, we give a new family of…

cs.DS2024

SoS Certifiability of Subgaussian Distributions and its Algorithmic Applications

Ilias Diakonikolas, Samuel B. Hopkins, Ankit Pensia +1

We prove that there is a universal constant $C > 0$ so that for every $d \in N$ , every centered subgaussian distribution $D$ on $R^{d}$ , and every even $p \in…

math.ST2023

Beyond Catoni: Sharper Rates for Heavy-Tailed and Robust Mean Estimation

Shivam Gupta, Samuel B. Hopkins, Eric Price

We study the fundamental problem of estimating the mean of a $d$ -dimensional distribution with covariance $Σ ≼ σ^{2} I_{d}$ given $n$ samples. When $d = 1$ , \cite{catoni} sho…

Algorithms with Polynomially-Improved Approximation Factors for the 2→q Norm, and Applications

SoS Certificates for Sparse Singular Values and Their Applications: Robust Statistics, Subspace Distortion, and More

SoS Certifiability of Subgaussian Distributions and its Algorithmic Applications

Beyond Catoni: Sharper Rates for Heavy-Tailed and Robust Mean Estimation

Algorithms with Polynomially-Improved Approximation Factors for the $2 \to q$ Norm, and Applications