126 citations · 126 across the 6 of their papers we have counts for
8 papers
Depth Separation for Neural Networks under Gaussian Measure
Cynthia Bortolotto, Francisco Ganacim, Roberto I. Oliveira
We revisit the problem of depth separation for neural networks, as studied by Eldan and Shamir, Daniely, and others. Specifically, we consider the natural setting of approxim…
Mean Testing under Truncation beyond Gaussian
Yuhao Wang, Roberto Imbuzeiro Oliveira, Themis Gouleakis
We characterize the fundamental limits of high-dimensional mean testing under arbitrary truncation, where samples are drawn from the conditional distribution for…
Robust, sub-Gaussian mean estimators in metric spaces
Daniel Bartl, Gabor Lugosi, Roberto Imbuzeiro Oliveira +1
Estimating the mean of a random vector from i.i.d. data has received considerable attention, and the optimal accuracy one may achieve with a given confidence is fairly well underst…
Counting communities in weighted Stochastic Block Models via semidefinite programming
Deborah Oliveira, Andressa Cerqueira, Roberto Oliveira
We consider the problem of estimating the number of communities in a weighted balanced Stochastic Block Model. We construct hypothesis tests based on semidefinite programming and w…
The top eigenvalue of uniformly random trees
Louigi Addario-Berry, Gábor Lugosi, Roberto Imbuzeiro Oliveira
Let be a uniformly random tree with vertex set , let be the largest vertex degree in , and let $λ_1({\mathbf…
Geometric planted matchings beyond the Gaussian model
Lucas da Rocha Schwengber, Roberto Imbuzeiro Oliveira
We consider the problem of recovering an unknown matching between a set of randomly placed points in and random perturbations of these points. This can be seen a…
On the quality of randomized approximations of Tukey's depth
Simon Briend, Gábor Lugosi, Roberto Imbuzeiro Oliveira
Tukey's depth (or halfspace depth) is a widely used measure of centrality for multivariate data. However, exact computation of Tukey's depth is known to be a hard problem in high d…
Efficient Generation of Generic Entanglement
R. Oliveira, O. C. O. Dahlsten, M. B. Plenio
We find that generic entanglement is physical, in the sense that it can be generated in polynomial time from two-qubit gates picked at random. We prove as the main result that such…