31 citations · 81 across the 9 of their papers we have counts for
14 papers
Tensor Moments of Gaussian Mixture Models: Theory and Applications
João M. Pereira, Joe Kileel, Tamara G. Kolda
Gaussian mixture models (GMMs) are fundamental tools in statistical and data sciences. We study the moments of multivariate Gaussians and GMMs. The -th moment of an -dimensio…
Landscape analysis of an improved power method for tensor decomposition
Joe Kileel, Timo Klock, João M. Pereira
In this work, we consider the optimization formulation for symmetric tensor decomposition recently introduced in the Subspace Power Method (SPM) of Kileel and Pereira. Unlike popul…
Modeling Extremes with d-max-decreasing Neural Networks
Ali Hasan, Khalil Elkhalil, Yuting Ng +4
We propose a novel neural network architecture that enables non-parametric calibration and generation of multivariate extreme value distributions (MEVs). MEVs arise from Extreme Va…
Identifying Latent Stochastic Differential Equations
Ali Hasan, João M. Pereira, Sina Farsiu +1
We present a method for learning latent stochastic differential equations (SDEs) from high-dimensional time series data. Given a high-dimensional time series generated from a lower…
Robust Marine Buoy Placement for Ship Detection Using Dropout K-Means
Yuting Ng, João M. Pereira, Denis Garagic +1
Marine buoys aid in the battle against Illegal, Unreported and Unregulated (IUU) fishing by detecting fishing vessels in their vicinity. Marine buoys, however, may be disrupted by…
Subspace power method for symmetric tensor decomposition
Joe Kileel, João M. Pereira
We introduce the Subspace Power Method (SPM) for calculating the CP decomposition of low-rank real symmetric tensors. This algorithm calculates one new CP component at a time, alte…
Learning Partial Differential Equations from Data Using Neural Networks
Ali Hasan, João M. Pereira, Robert Ravier +2
We develop a framework for estimating unknown partial differential equations from noisy data, using a deep learning approach. Given noisy samples of a solution to an unknown PDE, o…
Estimation in the group action channel
Emmanuel Abbe, João M. Pereira, Amit Singer
We analyze the problem of estimating a signal from multiple measurements on a $\mbox{group action channel}$ that linearly transforms a signal by a random group action followed by a…
Multireference Alignment is Easier with an Aperiodic Translation Distribution
Emmanuel Abbe, Tamir Bendory, William Leeb +3
In the multireference alignment model, a signal is observed by the action of a random circular translation and the addition of Gaussian noise. The goal is to recover the signal's o…
Sharp rates of convergence for accumulated spectrograms
Luís Daniel Abreu, João Pereira, José Luis Romero
We investigate an inverse problem in time-frequency localization: the approximation of the symbol of a time-frequency localization operator from partial spectral information by the…
Sample Complexity of the Boolean Multireference Alignment Problem
Emmanuel Abbe, Joao Pereira, Amit Singer
The Boolean multireference alignment problem consists in recovering a Boolean signal from multiple shifted and noisy observations. In this paper we obtain an expression for the err…
The Weyl-Heisenberg ensemble: hyperuniformity and higher Landau levels
Luís Daniel Abreu, João M. Pereira, José Luis Romero +1
Weyl-Heisenberg ensembles are a class of determinantal point processes associated with the Schrödinger representation of the Heisenberg group. Hyperuniformity characterizes a state…
Pseudo prolate spheroidal functions
Luís Daniel Abreu, João M. Pereira
Let and denote the operators which cut the time content outside and the frequency content outside , respectively. The prolate spheroidal functions are the ei…
Measures of localization and quantitative Nyquist densities
Luís Daniel Abreu, João M. Pereira
We obtain a refinement of the degrees of freedom estimate of Landau and Pollak. More precisely, we estimate, in terms of , the increase in the degrees of freedom resulting upon…