Modern machine learning paradigms, such as deep learning, occur in or cl...
In their seminal work, Polyak and Juditsky showed that stochastic
approx...
We investigate a clustering problem with data from a mixture of Gaussian...
Nonsmooth optimization problems arising in practice tend to exhibit
bene...
Recent work has shown that stochastically perturbed gradient methods can...
We introduce a geometrically transparent strict saddle property for nons...
Standard results in stochastic convex optimization bound the number of
s...
Stochastic (sub)gradient methods require step size schedule tuning to pe...
The task of recovering a low-rank matrix from its noisy linear measureme...
The blind deconvolution problem seeks to recover a pair of vectors from ...
We investigate the stochastic optimization problem of minimizing populat...
Given a nonsmooth, nonconvex minimization problem, we consider algorithm...
This work considers the question: what convergence guarantees does the
s...
We consider an algorithm that successively samples and minimizes stochas...
We prove that the projected stochastic subgradient method, applied to a
...
In this paper, we show how to transform any optimization problem that ar...
Acquisition cost is a crucial bottleneck for seismic workflows, and low-...
We propose an extension of popular descriptors based on gradient orienta...