2 citations · 3 across the 11 of their papers we have counts for
11 papers
Identification of Nonlinear Acyclic Networks in Continuous Time from Nonzero Initial Conditions and Full Excitations
Ramachandran Anantharaman, Renato Vizuete, Julien M. Hendrickx +1
This paper addresses the identifiability and identification of nonlinear acyclic networks in continuous time when the dynamics are located on the edges and all the nodes are excite…
On the Convex Interpolation for Linear Operators
Nizar Bousselmi, Zhicheng Deng, Jie Lu +2
The worst-case performance of an optimization method on a problem class can be analyzed using a finite description of the problem class, known as interpolation conditions. In this…
Numerical Design of Optimized First-Order Algorithms
Yassine Kamri, Julien M. Hendrickx, François Glineur
We derive several numerical methods for designing optimized first-order algorithms in unconstrained convex optimization settings. Our methods are based on the Performance Estimatio…
On the Worst-Case Analysis of Cyclic Block Coordinate Descent type Algorithms
Yassine Kamri, François Glineur, Julien M. Hendrickx +1
We study the worst-case behavior of Block Coordinate Descent (BCD) type algorithms for unconstrained minimization of coordinate-wise smooth convex functions. This behavior is indee…
Computer-aided analyses of stochastic first-order methods, via interpolation conditions for stochastic optimization
Anne Rubbens, Sébastien Colla, Julien M. Hendrickx
This work proposes a framework, embedded within the Performance Estimation framework (PEP), for obtaining worst-case performance guarantees on stochastic first-order methods. Given…
Performance Estimation of second-order optimization methods on classes of univariate functions
Anne Rubbens, Nizar Bousselmi, Julien M. Hendrickx +1
We develop a principled approach to obtain exact computer-aided worst-case guarantees on the performance of second-order optimization methods on classes of univariate functions. We…
A constructive approach to strengthen algebraic descriptions of function and operator classes
Anne Rubbens, Julien M. Hendrickx, Adrien Taylor
It is well known that functions (resp. operators) satisfying a property~ on a subset cannot necessarily be extended to a function (resp. operator) satisf…
A constraint-based approach to function interpolation, with application to performance estimation for weakly convex optimisation
Anne Rubbens, Julien M. Hendrickx
We consider the problem of obtaining interpolation constraints for function classes, i.e., necessary and sufficient constraints that a set of points, function values and (sub)gradi…
Comparison of Proximal First-Order Primal and Primal-Dual algorithms via Performance Estimation
Nizar Bousselmi, Nelly Pustelnik, Julien M. Hendrickx +1
Selecting the fastest algorithm for a specific signal/image processing task is a challenging question. We propose an approach based on the Performance Estimation Problem framework…
On the Set of Possible Minimizers of a Sum of Convex Functions
Moslem Zamani, François Glineur, Julien M. Hendrickx
Consider a sum of convex functions, where the only information known about each individual summand is the location of a minimizer. In this work, we give an exact characterization o…
Convex SGD: Generalization Without Early Stopping
Julien Hendrickx, Alex Olshevsky
We consider the generalization error associated with stochastic gradient descent on a smooth convex function over a compact set. We show the first bound on the generalization error…