Introduction to online nonstochastic control

E Hazan, K Singh - arXiv preprint arXiv:2211.09619, 2022 - arxiv.org
This text presents an introduction to an emerging paradigm in control of dynamical systems
and differentiable reinforcement learning called online nonstochastic control. The new …

[PDF][PDF] Greedy transaction fee mechanisms for (non-) myopic miners

Y Gafni, A Yaish - arXiv preprint arXiv:2210.07793, 2022 - researchgate.net
Cryptocurrencies such as Bitcoin [66] and Ethereum [10] facilitate money transactions
between users by relying on a decentralized process in which miners collect such …

Online non-stochastic control with partial feedback

YH Yan, P Zhao, ZH Zhou - Journal of Machine Learning Research, 2023 - jmlr.org
Online control with non-stochastic disturbances and adversarially chosen convex cost
functions, referred to as online non-stochastic control, has recently attracted increasing …

Augment Online Linear Optimization with Arbitrarily Bad Machine-Learned Predictions

D Wen, Y Li, FCM Lau - IEEE INFOCOM 2024-IEEE Conference …, 2024 - ieeexplore.ieee.org
The online linear optimization paradigm is important to many real-world network
applications as well as theoretical algorithmic studies. Recent studies have made attempts …

[HTML][HTML] Regret optimal control for uncertain stochastic systems

A Martin, L Furieri, F Dörfler, J Lygeros… - European Journal of …, 2024 - Elsevier
We consider control of uncertain linear time-varying stochastic systems from the perspective
of regret minimization. Specifically, we focus on the problem of designing a feedback …

The SMART approach to instance-optimal online learning

S Banerjee, A Bhatt, CL Yu - arXiv preprint arXiv:2402.17720, 2024 - arxiv.org
We devise an online learning algorithm--titled Switching via Monotone Adapted Regret
Traces (SMART)--that adapts to the data and achieves regret that is instance optimal, ie …

Optimistic Online Non-stochastic Control via FTRL

N Mhaisen, G Iosifidis - arXiv preprint arXiv:2404.03309, 2024 - arxiv.org
This paper brings the concept of" optimism" to the new and promising framework of online
Non-stochastic Control (NSC). Namely, we study how can NSC benefit from a prediction …

Adaptive online non-stochastic control

N Mhaisen, G Iosifidis - 6th Annual Learning for Dynamics & …, 2024 - proceedings.mlr.press
We tackle the problem of Non-stochastic Control (NSC) with the aim of obtaining algorithms
whose policy regret is proportional to the difficulty of the controlled environment. Namely, we …

Robust Online Convex Optimization for Disturbance Rejection

J Lai, P Seiler - arXiv preprint arXiv:2405.07037, 2024 - arxiv.org
Online convex optimization (OCO) is a powerful tool for learning sequential data, making it
ideal for high precision control applications where the disturbances are arbitrary and …

Safety Filter for Robust Disturbance Rejection via Online Optimization

J Lai, P Seiler - arXiv preprint arXiv:2411.09582, 2024 - arxiv.org
Disturbance rejection in high-precision control applications can be significantly improved
upon via online convex optimization (OCO). This includes classical techniques such as …