activity
20152026
most citedApproximating Continuous Functions by ReLU Nets of Minimal Width

130 citations · 209 across the 59 of their papers we have counts for

collaborators
Showing 2021Show all

7 papers · 1 filter

math.PR2021

Local algorithms for Maximum Cut and Minimum Bisection on locally treelike regular graphs of large degree

Ahmed El Alaoui, Andrea Montanari, Mark Sellke

Given a graph of degree over vertices, we consider the problem of computing a near maximum cut or a near minimum bisection in polynomial time. For graphs of girth ,…

math.PR2021★ 2 cited

Tight Lipschitz Hardness for Optimizing Mean Field Spin Glasses

Brice Huang, Mark Sellke

We study the problem of algorithmically optimizing the Hamiltonian of a spherical or Ising mixed -spin glass. The maximum asymptotic value of is cha…

cs.LG2021★ 4 cited

Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments

Yining Chen, Elan Rosenfeld, Mark Sellke +2

Domain generalization aims at performing well on unseen test environments with data from a limited number of training environments. Despite a proliferation of proposal algorithms f…

cs.LG2021

A Universal Law of Robustness via Isoperimetry

Sébastien Bubeck, Mark Sellke

Classically, data interpolation with a parametrized model class is possible as long as the number of parameters is larger than the number of equations to be satisfied. A puzzling p…

cond-mat.dis-nn2021★ 15 cited

Optimizing Mean Field Spin Glasses with External Field

Mark Sellke

We consider the Hamiltonians of mean-field spin glasses, which are certain random functions defined on high-dimensional cubes or spheres in . The asymptotic maxi…

math.GR2021

Tensor Quasi-Random Groups

Mark Sellke

Gowers has elegantly characterized the finite groups in which for any positive density subsets . This property, quasi-randomness, holds if and only…

math.PR2021

Cutoff for the Asymmetric Riffle Shuffle

Mark Sellke

In the Gilbert-Shannon-Reeds shuffle, a deck of cards is cut into two approximately equal parts which are then riffled uniformly at random. Bayer and Diaconis famously showed t…