activity
20112026
most citedSharp nonasymptotic bounds on the norm of random matrices with independent entries

202 citations · 1.3k across the 61 of their papers we have counts for

collaborators
Showing 2018Show all

7 papers · 1 filter

math.OC2018★ 4 cited

A Gramian Description of the Degree 4 Generalized Elliptope

Afonso S. Bandeira, Dmitriy Kunisky

One of the most widely studied convex relaxations in combinatorial optimization is the relaxation of the cut polytope to the elliptope , which correspo…

math.OC2018★ 3 cited

On the Landscape of Synchronization Networks: A Perspective from Nonconvex Optimization

Shuyang Ling, Ruitu Xu, Afonso S. Bandeira

Studying the landscape of nonconvex cost function is key towards a better understanding of optimization algorithms widely used in signal processing, statistics, and machine learnin…

math.ST2018★ 78 cited

Optimality and Sub-optimality of PCA I: Spiked Random Matrix Models

Amelia Perry, Alexander S. Wein, Afonso S. Bandeira +1

A central problem of random matrix theory is to understand the eigenvalues of spiked random matrix models, introduced by Johnstone, in which a prominent eigenvector (or "spike") is…

math.PR2018★ 31 cited

Stochastic Block Model for Hypergraphs: Statistical limits and a semidefinite programming approach

Chiheon Kim, Afonso S. Bandeira, Michel X. Goemans

We study the problem of community detection in a random hypergraph model which we call the stochastic block model for -uniform hypergraphs (-SBM). We investigate the exact re…

stat.ML2018

Notes on computational-to-statistical gaps: predictions using statistical physics

Afonso S. Bandeira, Amelia Perry, Alexander S. Wein

In these notes we describe heuristics to predict computational-to-statistical gaps in certain statistical problems. These are regimes in which the underlying statistical problem is…

math.OC2018★ 54 cited

Deterministic guarantees for Burer-Monteiro factorizations of smooth semidefinite programs

Nicolas Boumal, Vladislav Voroninski, Afonso S. Bandeira

We consider semidefinite programs (SDPs) with equality constraints. The variable to be optimized is a positive semidefinite matrix of size . Following the Burer--Monteiro ap…