activity
20192022
most citedOn the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs

4 citations · 5 across the 4 of their papers we have counts for

collaborators

11 papers

math.OC2022

Inexact GMRES Policy Iteration for Large-Scale Markov Decision Processes

Matilde Gargiani, Dominic Liao-McPherson, Andrea Zanelli +1

Policy iteration enjoys a local quadratic rate of contraction, but its iterations are computationally expensive for Markov decision processes (MDPs) with a large number of states.…

cs.LG20221 cited

PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation

Matilde Gargiani, Andrea Zanelli, Andrea Martinelli +2

Despite their success, policy gradient methods suffer from high variance of the gradient estimate, which can result in unsatisfactory sample complexity. Recently, numerous variance…

eess.SY2021

System Level Disturbance Reachable Sets and their Application to Tube-based MPC

Jerome Sieber, Andrea Zanelli, Samir Bennani +1

Tube-based model predictive control (MPC) methods leverage tubes to bound deviations from a nominal trajectory due to uncertainties in order to ensure constraint satisfaction. This…

cs.LG2020

Convergence Analysis of Homotopy-SGD for non-convex optimization

Matilde Gargiani, Andrea Zanelli, Quoc Tran-Dinh +2

First-order stochastic methods for solving large-scale non-convex optimization problems are widely used in many big-data applications, e.g. training deep neural networks as well as…

cs.RO2020

An Efficient Real-Time NMPC for Quadrotor Position Control under Communication Time-Delay

Barbara Barros Carlos, Tommaso Sartor, Andrea Zanelli +4

The advances in computer processor technology have enabled the application of nonlinear model predictive control (NMPC) to agile systems, such as quadrotors. These systems are char…

cs.LG20204 cited

On the Promise of the Stochastic Generalized Gauss-Newton Method for Training DNNs

Matilde Gargiani, Andrea Zanelli, Moritz Diehl +1

Following early work on Hessian-free methods for deep learning, we study a stochastic generalized Gauss-Newton method (SGN) for training DNNs. SGN is a second-order optimization me…