no code implementations • 17 Oct 2023 • Yoshio Ebihara, Xin Dai, Victor Magron, Dimitri Peaucelle, Sophie Tarbouriech
By following a standard procedure using multipliers that capture the behavior of ReLUs, we first reduce the upper bound computation problem of the local Lipschitz constant into a semidefinite programming problem (SDP).
no code implementations • 13 Sep 2022 • Ngoc Hoang Anh Mai, Victor Magron, Jean-Bernard Lasserre, Kim-Chuan Toh
We consider polynomial optimization problems (POP) on a semialgebraic set contained in the nonnegative orthant (every POP on a compact set can be put in this format by a simple translation of the origin).
2 code implementations • 23 Aug 2022 • Victor Magron, Jie Wang
Fortunately, for many applications, we can look at the problem in the eyes and exploit the inherent data structure arising from the cost and constraints describing the problem, for instance sparsity or symmetries.
no code implementations • 9 Feb 2022 • Yoshio Ebihara, Hayato Waki, Victor Magron, Ngoc Hoang Anh Mai, Dimitri Peaucelle, Sophie Tarbouriech
To get around this difficulty, we loosen the standard positive semidefinite cone to the copositive cone, and employ copositive multipliers to capture the nonnegativity properties.
no code implementations • 3 Feb 2021 • Ngoc Hoang Anh Mai, Abhishek Bhardwaj, Victor Magron
In this article, we show that each semidefinite relaxation of a ball-constrained noncommutative polynomial optimization problem can be cast as a semidefinite program with a constant trace matrix variable.
Optimization and Control
1 code implementation • 13 Jan 2021 • Tong Chen, Jean-Bernard Lasserre, Victor Magron, Edouard Pauwels
We introduce a sublevel Moment-SOS hierarchy where each SDP relaxation can be viewed as an intermediate (or interpolation) between the d-th and (d+1)-th order SDP relaxations of the Moment-SOS hierarchy (dense or sparse version).
Combinatorial Optimization Optimization and Control
no code implementations • 10 Dec 2020 • Jean Bernard Lasserre, Victor Magron, Swann Marx, Olivier Zahm
This paper is concerned with minimizing a sum of rational functions over a compact set of high-dimension.
Optimization and Control
no code implementations • 22 Jun 2020 • Igor Klep, Victor Magron, Jurij Volčič
Motivated by recent progress in quantum information theory, this article aims at optimizing trace polynomials, i. e., polynomials in noncommuting variables and traces of their products.
Mathematical Physics Functional Analysis Mathematical Physics Optimization and Control 46N50, 90C22, 47N10, 13J30
1 code implementation • 4 Mar 2020 • Jie Wang, Victor Magron, Jean-Bernard Lasserre
The novelty and distinguishing feature of such relaxations is to obtain quasi block-diagonal matrices obtained in an iterative procedure that performs chordal extension of certain adjacency graphs.
Optimization and Control 14P10, 90C25, 12D15, 12Y05
2 code implementations • NeurIPS 2020 • Tong Chen, Jean-Bernard Lasserre, Victor Magron, Edouard Pauwels
The Lipschitz constant of a network plays an important role in many applications of deep learning, such as robustness certification and Wasserstein Generative Adversarial Network.
3 code implementations • 18 Dec 2019 • Jie Wang, Victor Magron, Jean-Bernard Lasserre
This paper is concerned with polynomial optimization problems.
Optimization and Control
2 code implementations • 26 Nov 2019 • Ngoc Hoang Anh Mai, Jean-Bernard Lasserre, Victor Magron
As a consequence, it allows one to define a hierarchy of semidefinite relaxations for a general polynomial optimization problem.
Optimization and Control