3 citations · 3 across the 4 of their papers we have counts for
4 papers · 1 filter
A new use of the Kurdyka-Lojasiewicz property to study asymptotic behaviours of some stochastic optimization algorithms in a non-convex differentiable framework
Jean-Baptiste Fest
The asymptotic analysis of a generic stochastic optimization algorithm mainly relies on the establishment of a specific descent condition. While the convexity assumption allows for…
A new non-convex framework to improve asymptotical knowledge on generic stochastic gradient descent
Jean-Baptiste Fest, Audrey Repetti, Emilie Chouzenoux
Stochastic gradient optimization methods are broadly used to minimize non-convex smooth objective functions, for instance when training deep neural networks. However, theoretical g…
A stochastic use of the Kurdyka-Lojasiewicz property: Investigation of optimization algorithms behaviours in a non-convex differentiable framework
Jean-Baptiste Fest, Audrey Repetti, Emilie Chouzenoux
Stochastic differentiable approximation schemes are widely used for solving high dimensional problems. Most of existing methods satisfy some desirable properties, including conditi…
On a fixed-point continuation method for a convex optimization problem
Jean-Baptiste Fest, Tommi Heikkilä, Ignace Loris +4
We consider a variation of the classical proximal-gradient algorithm for the iterative minimization of a cost function consisting of a sum of two terms, one smooth and the other pr…