works on

From the 1 of 12 linked papers with an AI index.

collaborators

12 papers

math.OC2026

Learning to control switching nonlinear systems with Koopman operator regression

Edoardo Caldarelli, Oleksii Kachaiev, Cesare Molinari +1

The paper proposes using Koopman operator regression in a reproducing kernel Hilbert space to identify and control nonlinear systems with finite action spaces, creating a linear sw…

math.OC2026

Frank-Wolfe with Moreau Envelope Smoothing for Nonsmooth Nonconvex Problems

Antonio Silveti-Falls, Cesare Molinari, Zev Woodstock

We present and analyze Frank-Wolfe with Moreau Envelope Smoothing (FRAMES) for solving nonsmooth nonconvex constrained optimization problems, taking advantage of iterative smoothin…

cs.LG2026

Proximal basin hopping: global optimization with guarantees

Guillaume Lauga, Cesare Molinari, Samuel Vaiter

Global optimization is a challenging problem, with plenty of algorithms displaying empirical success, but scarce theoretical backing. In this work, we propose a new theoretical fra…

math.OC2026

Convergence of zeroth-order proximal point algorithms in the high-temperature regime

Emanuele Naldi, Hippolyte Labarrière, Cesare Molinari +1

Efficient methods for non-convex black-box optimization largely rely on sampling. In this context, the Zeroth-Order Proximal Operator (ZOPO) and the corresponding Zeroth-Order Prox…

cs.LG2026

SGD for Variational Inference: Tackling Unbounded Variance via Preconditioning and Dynamic Batching

Hippolyte Labarrière, Cesare Molinari, Silvia Villa +1

Black-Box Variational Inference (BBVI) typically relies on Stochastic Gradient Descent (SGD) to optimize the Evidence Lower Bound (ELBO). However, the stochastic gradients in BBVI…

cs.LG2026

Optimization Insights into Deep Diagonal Linear Networks

Hippolyte Labarrière, Cesare Molinari, Lorenzo Rosasco +2

Gradient-based methods successfully train highly overparameterized models in practice, even though the associated optimization problems are markedly nonconvex. Understanding the me…