4 citations · 4 across the 12 of their papers we have counts for
13 papers
Optimization by Reparametrization: Time-Warped Mirror Flows with Singular Geometry
Cristian Vega, Cesare Molinari, Lorenzo Rosasco +1
Solving data-driven problems requires defining complex models and fitting them to data, neural networks being a motivating example. The fitting procedure can be seen as an optimiza…
Learning Ergodic Dynamical Systems from a Finite Trajectory
Oleksii Kachaiev, Silvia Villa, Lorenzo Rosasco
We consider the problem of learning from a single finite trajectory of an ergodic stochastic dynamical system. More precisely, we study discrete-time autonomous stochastic systems…
Langevin for Nonconvex Optimization: Exact, Inexact and Zeroth-Order
Emanuele Naldi, Marco Rando, Lorenzo Rosasco +1
We study Langevin-based methods for non-convex optimization under smoothness and dissipativity assumptions, focusing on non-asymptotic expected excess-risk bounds rather than sampl…
Learning to control switching nonlinear systems with Koopman operator regression
Edoardo Caldarelli, Oleksii Kachaiev, Cesare Molinari +1
In this work, we consider the identification and control of nonlinear systems with finite action spaces. The unknown dynamics are estimated from finite samples with Koopman operato…
Dynamic robotic cloth folding with efficient Koopman operator-based model predictive control
Edoardo Caldarelli, Franco Coltraro, Adrià Colomé +2
Robotic cloth folding is a challenging task, particularly when considering dynamic folding tasks, which aim at folding cloth by fast motions that leverage its dynamics. When subjec…
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…
On the Sample Complexity of Learning for Blind Inverse Problems
Nathan Buskulic, Luca Calatroni, Lorenzo Rosasco +1
Blind inverse problems arise in many experimental settings where both the signal of interest and the forward operator are (partially) unknown. In this context, methods developed fo…
A Proximal Stochastic Variance Reduced Zeroth-order Algorithm using Structured Finite-Differences
Marco Rando, Cheik Traoré, Cesare Molinari +2
Minimizing finite sums of functions is a central problem in optimization, arising in numerous practical applications. Such problems are commonly addressed using first-order optimiz…
A Structured Tour of Optimization with Finite Differences
Marco Rando, Cesare Molinari, Lorenzo Rosasco +1
Finite-difference methods are widely used for zeroth-order optimization in settings where gradient information is unavailable or expensive to compute. These procedures mimic first-…
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…
Automatic Gain Tuning for Humanoid Robots Walking Architectures Using Gradient-Free Optimization Techniques
Carlotta Sartore, Marco Rando, Giulio Romualdi +3
Developing sophisticated control architectures has endowed robots, particularly humanoid robots, with numerous capabilities. However, tuning these architectures remains a challengi…
A New Formulation for Zeroth-Order Optimization of Adversarial EXEmples in Malware Detection
Marco Rando, Luca Demetrio, Lorenzo Rosasco +1
Machine learning malware detectors are vulnerable to adversarial EXEmples, i.e., carefully-crafted Windows programs tailored to evade detection. Unlike other adversarial problems,…
Linear quadratic control of nonlinear systems with Koopman operator learning and the Nyström method
Edoardo Caldarelli, Antoine Chatalic, Adrià Colomé +4
In this paper, we study how the Koopman operator framework can be combined with kernel methods to effectively control nonlinear dynamical systems. While kernel methods have typical…