Renewable energy integration is an effective measure to resolve environmental problems and implement sustainable development, yet the volatility of wind and solar generation has …
C Yu, G Shi, SJ Chung, Y Yue… - Advances in Neural …, 2020 - proceedings.neurips.cc
We study the impact of predictions in online Linear Quadratic Regulator control with both stochastic and adversarial disturbances in the dynamics. In both settings, we characterize …
N Christianson, J Shen… - … Conference on Artificial …, 2023 - proceedings.mlr.press
We examine the problem of designing learning-augmented algorithms for metrical task systems (MTS) that exploit machine-learned advice while maintaining rigorous, worst-case …
We study predictive control in a setting where the dynamics are time-varying and linear, and the costs are time-varying and well-conditioned. At each time step, the controller receives …
Y Lin, Y Hu, G Qu, T Li… - Advances in Neural …, 2022 - proceedings.neurips.cc
Abstract We study Model Predictive Control (MPC) and propose a general analysis pipeline to bound its dynamic regret. The pipeline first requires deriving a perturbation bound for a …
Contextual Bayesian optimization (CBO) is a powerful framework for sequential decision- making given side information, with important applications, eg, in wind energy systems. In …
This paper presents competitive algorithms for a novel class of online optimization problems with memory. We consider a setting where the learner seeks to minimize the sum of a hitting …
P Li, J Yang, A Wierman, S Ren - Advances in Neural …, 2024 - proceedings.neurips.cc
We study a general form of Smoothed Online Convex Optimization, aka SOCO, including multi-step switching costs and feedback delay. We propose a novel machine learning (ML) …
G Goel, B Hassibi - arXiv preprint arXiv:2010.10473, 2020 - arxiv.org
We consider control in linear time-varying dynamical systems from the perspective of regret minimization. Unlike most prior work in this area, we focus on the problem of designing an …