English
Related papers

Related papers: Primal-dual Estimator Learning: an Offline Constra…

200 papers

We study offline reinforcement learning (RL) with linear MDPs under the infinite-horizon discounted setting which aims to learn a policy that maximizes the expected discounted cumulative reward using a pre-collected dataset. Existing…

Machine Learning · Statistics 2024-06-04 Kihyuk Hong , Ambuj Tewari

Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy. This problem has attracted a lot of attention recently, but most existing methods with strong…

Machine Learning · Computer Science 2023-05-23 Germano Gabbianelli , Gergely Neu , Nneka Okolo , Matteo Papini

The extension of classical online algorithms when provided with predictions is a new and active research area. In this paper, we extend the primal-dual method for online algorithms in order to incorporate predictions that advise the online…

Machine Learning · Computer Science 2020-10-23 Étienne Bamas , Andreas Maggiori , Ola Svensson

The domain of online algorithms with predictions has been extensively studied for different applications such as scheduling, caching (paging), clustering, ski rental, etc. Recently, Bamas et al., aiming for an unified method, have provided…

Data Structures and Algorithms · Computer Science 2021-10-04 Nguyen Kim Thang , Christoph Durr

Online optimisation facilitates the solution of dynamic inverse problems, such as image stabilisation, fluid flow monitoring, and dynamic medical imaging. In this paper, we improve upon previous work on predictive online primal-dual methods…

Optimization and Control · Mathematics 2025-02-28 Neil Dizon , Jyrki Jauhiainen , Tuomo Valkonen

Robust stability of moving-horizon estimators is investigated for nonlinear discrete-time systems that are detectable in the sense of incremental input/output-to-state stability and are affected by disturbances. The estimate of a…

Systems and Control · Electrical Eng. & Systems 2025-01-08 Angelo Alessandri

This paper introduces a novel optimization-based approach for parametric nonlinear system identification. Building upon the prediction error method framework, traditionally used for linear system identification, we extend its capabilities…

Optimization and Control · Mathematics 2024-03-27 Léo Simpson , Jonas Asprion , Simon Muntwiler , Johannes Köhler , Moritz Diehl

This paper studies how to train machine-learning models that directly approximate the optimal solutions of constrained optimization problems. This is an empirical risk minimization under constraints, which is challenging as training must…

Machine Learning · Computer Science 2022-11-24 Seonho Park , Pascal Van Hentenryck

In this work, an innovative data-driven moving horizon state estimation is proposed for model dynamic-unknown systems based on Bayesian optimization. As long as the measurement data is received, a locally linear dynamics model can be…

Systems and Control · Electrical Eng. & Systems 2023-11-14 Qing Sun , Shuai Niu , Minrui Fei

We study online learning problems in which a decision maker has to make a sequence of costly decisions, with the goal of maximizing their expected reward while adhering to budget and return-on-investment (ROI) constraints. Existing…

Computer Science and Game Theory · Computer Science 2024-03-05 Matteo Castiglioni , Andrea Celli , Christian Kroer

In this paper, we propose a novel framework for approximating the explicit MPC law for linear parameter-varying systems using supervised learning. In contrast to most existing approaches, we not only learn the control policy, but also a…

Machine Learning · Computer Science 2019-06-21 Xiaojing Zhang , Monimoy Bujarbaruah , Francesco Borrelli

This work develops new algorithms with rigorous efficiency guarantees for infinite horizon imitation learning (IL) with linear function approximation without restrictive coherence assumptions. We begin with the minimax formulation of the…

Machine Learning · Computer Science 2023-05-31 Luca Viano , Angeliki Kamoutsi , Gergely Neu , Igor Krawczuk , Volkan Cevher

This paper proposes an algorithm that combines Fast Moving Horizon Parameter Estimation and Model Predictive Control subject to an observability constraint designed to ensure a lower bound on the performance of the parameter estimator.…

Optimization and Control · Mathematics 2023-03-27 Emilien Flayac , Girish Nair , Iman Shames

In this paper, we consider optimizing a smooth, convex, lower semicontinuous function in Riemannian space with constraints. To solve the problem, we first convert it to a dual problem and then propose a general primal-dual algorithm to…

Machine Learning · Computer Science 2020-05-20 Shijun Wang , Baocheng Zhu , Lintao Ma , Yuan Qi

Real-time computation of optimal control is a challenging problem and, to solve this difficulty, many frameworks proposed to use learning techniques to learn (possibly sub-optimal) controllers and enable their usage in an online fashion.…

A recent line of research investigates how algorithms can be augmented with machine-learned predictions to overcome worst case lower bounds. This area has revealed interesting algorithmic insights into problems, with particular success in…

Machine Learning · Computer Science 2021-07-22 Michael Dinitz , Sungjin Im , Thomas Lavastida , Benjamin Moseley , Sergei Vassilvitskii

In many practical applications of constrained optimization, scale and solving time limits make traditional optimization solvers prohibitively slow. Thus, the research question of how to design optimization proxies -- machine learning models…

Machine Learning · Computer Science 2025-02-14 Michael Klamkin , Mathieu Tanneau , Pascal Van Hentenryck

We present a primal-dual algorithmic framework to obtain approximate solutions to a prototypical constrained convex optimization problem, and rigorously characterize how common structural assumptions affect the numerical efficiency. Our…

Optimization and Control · Mathematics 2015-03-04 Quoc Tran-Dinh , Volkan Cevher

In this work we combine two distinct machine learning methodologies, sequential Monte Carlo and Bayesian experimental design, and apply them to the problem of inferring the dynamical parameters of a quantum system. We design the algorithm…

Quantum Physics · Physics 2012-10-10 Christopher E. Granade , Christopher Ferrie , Nathan Wiebe , D. G. Cory

We propose a moving horizon estimation scheme to estimate the states and the unknown constant parameters of general nonlinear uncertain discrete-time systems. The proposed framework and analysis explicitly do not involve the a priori…

Systems and Control · Electrical Eng. & Systems 2025-12-22 Julian D. Schiller , Matthias A. Müller
‹ Prev 1 2 3 10 Next ›