Publications related to A PAC-Bayesian Framework for Optimal Control with Stability Guarantees

Related publications (16)

Masked Diffusion Strategy for Privacy-Preserving Distributed Learning

To protect both local gradients and estimated parameters in distributed learning, this paper introduces a masked diffusion (MD) strategy, leading to two algorithms: the MD stochastic gradient (MD-SG) and the MD primal-dual stochastic gradient (MPD-SG). The ...

2025

Learning Hand State Estimation for a Light Exoskeleton

Luca Randazzo

We propose a machine learning-based estimator of the hand state for rehabilitation purposes, using light exoskeletons. These devices are easy to use and useful for delivering domestic and frequent therapies. We build a supervised approach using information ...

Springer Nature2025

Function-Space Optimality of Neural Architectures with Multivariate Nonlinearities

Michaël Unser, Rahul Parhi

We investigate the function-space optimality (specifically, the Banach-space optimality) of a large class of shallow neural architectures with multivariate nonlinearities/activation functions. To that end, we construct a new family of Banach spaces defined ...

SIAM PUBLICATIONS2025

Surface distributions and vertical profiles of trace gases (CO, O3, NO, NO2) in the Arctic wintertime boundary layer using low-cost sensors during ALPACA-2022

Julia Schmale, Andrea Baccarini, Roman Pohorsky

Electrochemical gas sensors (EGSs) have been used to measure the surface distributions and vertical profiles of trace gases in the wintertime Arctic boundary layer during the Alaskan Layered Pollution and Chemical Analysis (ALPACA) field experiment in Fair ...

COPERNICUS GESELLSCHAFT MBH2025

Ion Sieving in Two-Dimensional Membranes from First Principles

Nicola Marzari, Nicéphore Arthur François Bonnet

A first-principles approach for calculating ion separation in solution through two-dimensional (2D) membranes is proposed and applied. Ionic energy profiles across the membrane are obtained first, where solvation effects are simulated explicitly with machi ...

2025

Combinatorial Aspects of Continuous Optimization: Graph Polynomials and Neural Networks

Amire Bendjeddou

In this thesis, we study how combinatorial structures and symmetries emerge from analytic properties of graph polynomials and neural networks. Graph polynomials encode combinatorial aspects of the underlying graph in their coefficients and are remarkably u ...

EPFL2025

Upgrading SPHERE with the second stage AO system SAXO+: frequency-based data-driven controller for adaptive optics

Alireza Karimi, Vaibhav Gupta

This study introduces a novel frequency-based data-driven controller for adaptive optics, using power spectral density for optimization while ensuring stability criteria. It addresses disturbance rejection, command amplitude constraints and system transfer ...

SPIE2024

Efficient Recursive Data-enabled Predictive Control

Colin Neil Jones, Yingzhao Lian, Jicheng Shi

In the field of model predictive control, Dataenabled Predictive Control (DeePC) offers direct predictive control, bypassing traditional modeling. However, challenges emerge with increased computational demand due to recursive data updates. This paper intr ...

IEEE2024

How Two-Layer Neural Networks Learn, One (Giant) Step at a Time

Florent Gérard Krzakala, Bruno Loureiro, Ludovic Théo Stephan, Yatin Dandi, Luca Pesce

For high-dimensional Gaussian data, we investigate theoretically how the features of a two-layer neural network adapt to the structure of the target function through a few large batch gradient descent steps, leading to an improvement in the approximation c ...

2024

Rehabilitation exoskeleton system with bidirectional virtual reality feedback training strategy

Rui Wu

Virtual reality (VR) technology revitalises rehabilitation training by creating rich, interactive virtual rehabilitation scenes and tasks that deeply engage patients. Robotics with immersive VR environments have the potential to significantly enhance the s ...

2024

Euclid preparation XXXIII. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong-lensing events

Frédéric Courbin, Georges Meylan, Georgios Vernardos, Benjamin Yvan Alexandre Clement

Forthcoming imaging surveys will increase the number of known galaxy-scale strong lenses by several orders of magnitude. For this to happen, images of billions of galaxies will have to be inspected to identify potential candidates. In this context, deep-le ...

Edp Sciences S A2024

Simultaneous Quantification of Multiple Drugs by Machine Learning on Electrochemical Sensors

Sandro Carrara, Lin Du, Tatsunori Matsumoto

Electrochemical devices and systems are significant for the development of therapeutic drug monitoring (TDM) and personalized therapy. However, electrochemical sensors are usually not that much selective. Therefore, innovative machine learning (ML) approac ...

Institute of Electrical and Electronics Engineers Inc.2024

Logic Learning From Demonstrations for Multi-Step Manipulation Tasks in Dynamic Environments

Sylvain Calinon, Teng Xue, Amirreza Razmjoo Fard

Learning from Demonstration (LfD) stands as an efficient framework for imparting human-like skills to robots. Nevertheless, designing an LfD framework capable of seamlessly imitating, generalizing, and reacting to disturbances for long-horizon manipulation ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2024

Aircraft Departures Management for Low Altitude Air City Transport based on Macroscopic Fundamental Diagram

Nikolaos Geroliminis

Low-altitude aircraft is being developed as a new mode of urban transport. This will give rise to new urban air transport systems, called low-altitude air city transport (LAAT) systems. Recent works show that the Macroscopic Fundamental Diagram (MFD) is a ...

IEEE2023

HyperMixer: An MLP-based Low Cost Alternative to Transformers

Fabio James Fehr, François Fleuret, Arnaud Pannatier, Haolin Chen

Transformer-based architectures are the model of choice for natural language understanding, but they come at a significant cost, as they have quadratic complexity in the input length, require a lot of training data, and can be difficult to tune. In the pur ...

Assoc Computational Linguistics-Acl2023

Implementation and parametric study of J-integral data reduction methods for the translaminar toughness of hierarchical thin-ply composites

Véronique Michaud, Guillaume Clément Broggi

Three different J-integral formulations to derive the experimental translaminar toughness of composites from compact tension tests with a large-scale fracture process zone are implemented and discussed. They improve the existing approaches by taking advant ...

2023