Publications associées à Learning to Optimize with Convergence Guarantees Using Nonlinear System Theory

Publications associées (25)

Data-driven control in atomic force microscopy using a genetic algorithm

Increasing the scanning speed in Atomic Force Microscopy (AFM) relies on improving the tracking performance in the vertical direction of motion. The lightly damped resonances of piezo-actuators utilized in AFM nano-positioning stages hinder the maximum ach ...

2025

Improving the accuracy and interpretability of neural networks for wind power forecasting

Fernando Porté Agel, Jiannong Fang, Wenlong Liao

Deep neural networks (DNNs) are receiving increasing attention in wind power forecasting due to their ability to effectively capture complex patterns in wind data. However, their forecast errors are severely limited by the local optimal weight issue in opt ...

2025

Accelerating Spectral Clustering under Fairness Constraints

Volkan Cevher

Fairness of decision-making algorithms is an increasingly important issue. In this paper, we focus on spectral clustering with group fairness constraints, where every demographic group is represented in each cluster proportionally as in the general populat ...

2025

Decentralized gradient tracking with local steps

Anastasiia Koloskova

Gradient tracking (GT) is an algorithm designed for solving decentralized optimization problems over a network (such as training a machine learning model). A key feature of GT is a tracking mechanism that allows us to overcome data heterogeneity between no ...

2024

WILD SOLUTIONS TO SCALAR EULER-LAGRANGE EQUATIONS

Carl Johan Peter Johansson

. We study very weak solutions to scalar Euler-Lagrange equations associated with quadratic convex functionals. We investigate whether W1,1 solutions are necessarily W 1,2 Nash and Schauder applicable. We answer this question positively for a suitable clas ...

Amer Mathematical Soc2024

Diffusion Moving-Average Adaptation Over Networks

Ali H. Sayed

Recently, the diffusion moving-average (D-MA) scheme has been proposed as a way to combat noisy links over adaptive networks. However, the current theoretical results focus on networks with mean-square error costs where the optimal local solution agrees wi ...

2024

Learning Barrier-Certified Polynomial Dynamical Systems for Obstacle Avoidance with Robots

Aude Billard

Established techniques that enable robots to learn from demonstrations are based on learning a stable dynamical system (DS). To increase the robots' resilience to perturbations during tasks that involve static obstacle avoidance, we propose incorporating b ...

IEEE2024

CONFIG: Constrained Efficient Global Optimization for Closed-Loop Control System Optimization with Unmodeled Constraints

Colin Neil Jones, Yuning Jiang, Wenjie Xu

In this paper, the CONFIG algorithm, a simple and provably efficient constrained global optimization algorithm, is applied to optimize the closed-loop control performance of an unknown system with unmodeled constraints. Existing Gaussian process based clos ...

Elsevier2023

Multi-Level Monte Carlo Methods for Uncertainty Quantification and Risk-Averse Optimisation

Sundar Subramaniam Ganesh

This work aims to study the effects of wind uncertainties in civil engineering structural design. Optimising the design of a structure for safety or operability without factoring in these uncertainties can result in a design that is not robust to these per ...

EPFL2022

On improving the efficiency of modifier adaptation via directional information

Dominique Bonvin

In real-time optimization, the solution quality depends on the model ability to predict the plant KarushKuhn-Tucker (KKT) conditions. In the case of non-parametric plant-model mismatch, one can add input-affine modifiers to the model cost and constraints a ...

PERGAMON-ELSEVIER SCIENCE LTD2022

An Accelerated First-Order Method for Non-convex Optimization on Manifolds

Christopher Arnold Criscitiello, Nicolas Boumal

We describe the first gradient methods on Riemannian manifolds to achieve accelerated rates in the non-convex case. Under Lipschitz assumptions on the Riemannian gradient and Hessian of the cost function, these methods find approximate first-order critical ...

SPRINGER2022

Mixed Nash Equilibria in the Adversarial Examples Game

Rafaël Benjamin Pinot

This paper tackles the problem of adversarial examples from a game theoretic point of view. We study the open question of the existence of mixed Nash equilibria in the zero-sum game formed by the attacker and the classifier. While previous works usually al ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2021

A Multi-Agent Primal-Dual Strategy for Composite Optimization over Distributed Features

Ali H. Sayed, Sulaiman A S A E Alghunaim

This work studies multi-agent sharing optimization problems with the objective function being the sum of smooth local functions plus a convex (possibly non-smooth) function coupling all agents. This scenario arises in many machine learning and engineering ...

IEEE2020

A new wake model and comparison of eight algorithms for layout optimization of wind farms in complex terrain

Fernando Porté Agel

Layout optimization of wind farms constitutes an important and challenging task in complex terrain. This is especially due to the complex interactions of the boundary layer flows in complex terrain and wind turbine wakes, which renders wake modelling in co ...

ELSEVIER SCI LTD2020

Real-time control of an electric vehicle charging station while tracking an aggregated power-setpoint

Mario Paolone, Jean-Yves Le Boudec, Lorenzo Enrique Reyes Chamorro, Cong Wang, Roman Rudnik, Jagdish Prasad Achara

An electric vehicle (EV) charging method which considers the EVs heterogeneity, taking into account the absence of any information about future arrivals and departures, and of the amount of time any charging will take. The method further considers both swi ...

2020

Linear Speedup In Saddle-Point Escape For Decentralized Non-Convex Optimization

Ali H. Sayed, Stefan Vlaski

Under appropriate cooperation protocols and parameter choices, fully decentralized solutions for stochastic optimization have been shown to match the performance of centralized solutions and result in linear speedup (in the number of agents) relative to no ...

IEEE2020

Enforcing optimal operation in solid-oxide fuel-cell systems

Dominique Bonvin, Jan Van Herle, Christophe Salzmann, Timm Faulwasser, Zacharie Wuillemin, Tafarel de Avila Ferreira

This paper describes an optimization strategy for operating solid-oxide fuel-cell systems at optimal efficiency. Specifically, we present the experimental validation of a real-time optimization (RTO) strategy applied to a commercial solid-oxide fuel-cell s ...

2019

Streaming Principal Component Analysis From Incomplete Data

Armin Eftekhari

Linear subspace models are pervasive in computational sciences and particularly used for large datasets which are often incomplete due to privacy issues or sampling constraints. Therefore, a critical problem is developing an efficient algorithm for detecti ...

Microtome Publishing2019

Linear-parameter-varying approximation of nonlinear dynamics for model predictive flow control of urban multi-region systems

Nikolaos Geroliminis, Mohammadreza Saeedmanesh, Anastasios Kouvelas

An alternative approach for real-time network- wide traffic control in cities that has recently gained a lot of interest is perimeter flow control. The focus of the current work is to study two aspects that are not covered in the perimeter control literatu ...

2019

Sharp sphere packings

Maryna Viazovska

In this talk we will speak about recent progress on the sphere packing problem. The packing problem can be formulated for a wide class of metric spaces equipped with a measure. An interesting feature of this optimization problem is that a slight change of ...

World Scientific Publishing2018