71 citations · 151 across the 51 of their papers we have counts for
7 papers · 1 filter
A Comparison of Nonsmooth, Nonconvex, Constrained Optimization Solvers for the Design of Time-Delay Compensators
Vyacheslav Kungurtsev, Tim Mitchell, Tomas Vyhlidal
We present a detailed set of performance comparisons of two state-of-the-art solvers for the application of designing time-delay compensators, an important problem in the field of…
A Subsampling Line-Search Method with Second-Order Results
El-houcine Bergou, Youssef Diouane, Vladimir Kunc +2
In many contemporary optimization problems such as those arising in machine learning, it can be computationally challenging or even infeasible to evaluate an entire function or its…
Second-order Guarantees of Distributed Gradient Algorithms
Amir Daneshmand, Gesualdo Scutari, Vyacheslav Kungurtsev
We consider distributed smooth nonconvex unconstrained optimization over networks, modeled as a connected graph. We examine the behavior of distributed gradient-based algorithms ne…
A stochastic Levenberg-Marquardt method using random models with complexity results
E. Bergou, Y. Diouane, V. Kungurtsev +1
Globally convergent variants of the Gauss-Newton algorithm are often the methods of choice to tackle nonlinear least-squares problems. Among such frameworks, Levenberg-Marquardt an…
Algorithms for solving optimization problems arising from deep neural net models: nonsmooth problems
Vyacheslav Kungurtsev, Tomas Pevny
Machine Learning models incorporating multiple layered learning networks have been seen to provide effective models for various classification problems. The resulting optimization…
Algorithms for solving optimization problems arising from deep neural net models: smooth problems
Vyacheslav Kungurtsev, Tomas Pevny
Machine Learning models incorporating multiple layered learning networks have been seen to provide effective models for various classification problems. The resulting optimization…
A Two-Step Pre-Processing for Semidefinite Programming
Vyacheslav Kungurtsev, Jakub Marecek
In semidefinite programming (SDP), a number of pre-processing techniques have been developed including chordal-completion procedures, which reduce the dimension of individual const…