202 citations · 1.3k across the 61 of their papers we have counts for
10 papers · 1 filter
Tightness of the maximum likelihood semidefinite relaxation for angular synchronization
Afonso S. Bandeira, Nicolas Boumal, Amit Singer
Maximum likelihood estimation problems are, in general, intractable optimization problems. As a result, it is common to approximate the maximum likelihood estimator (MLE) using con…
A conditional construction of restricted isometries
Afonso S. Bandeira, Dustin G. Mixon, Joel Moreira
We study the restricted isometry property of a matrix that is built from the discrete Fourier transform matrix by collecting rows indexed by quadratic residues. We find an su…
Sharp nonasymptotic bounds on the norm of random matrices with independent entries
Afonso S. Bandeira, Ramon van Handel
We obtain nonasymptotic bounds on the spectral norm of random matrices with independent entries that improve significantly on earlier results. If is the symmetric m…
Relax, no need to round: integrality of clustering formulations
Pranjal Awasthi, Afonso S. Bandeira, Moses Charikar +3
We study exact recovery conditions for convex relaxations of point cloud clustering problems, focusing on two of the most common optimization problems for unsupervised clustering:…
Derandomizing restricted isometries via the Legendre symbol
Afonso S. Bandeira, Matthew Fickus, Dustin G. Mixon +1
The restricted isometry property (RIP) is an important matrix condition in compressed sensing, but the best matrix constructions to date use randomness. This paper leverages pseudo…
Exact Recovery in the Stochastic Block Model
Emmanuel Abbe, Afonso S. Bandeira, Georgina Hall
The stochastic block model (SBM) with two communities, or equivalently the planted bisection model, is a popular model of random graph exhibiting a cluster behaviour. In the symmet…