Introduction to online nonstochastic control
This text presents an introduction to an emerging paradigm in control of dynamical systems
and differentiable reinforcement learning called online nonstochastic control. The new …
and differentiable reinforcement learning called online nonstochastic control. The new …
[PDF][PDF] Greedy transaction fee mechanisms for (non-) myopic miners
Cryptocurrencies such as Bitcoin [66] and Ethereum [10] facilitate money transactions
between users by relying on a decentralized process in which miners collect such …
between users by relying on a decentralized process in which miners collect such …
Online non-stochastic control with partial feedback
Online control with non-stochastic disturbances and adversarially chosen convex cost
functions, referred to as online non-stochastic control, has recently attracted increasing …
functions, referred to as online non-stochastic control, has recently attracted increasing …
Augment Online Linear Optimization with Arbitrarily Bad Machine-Learned Predictions
The online linear optimization paradigm is important to many real-world network
applications as well as theoretical algorithmic studies. Recent studies have made attempts …
applications as well as theoretical algorithmic studies. Recent studies have made attempts …
[HTML][HTML] Regret optimal control for uncertain stochastic systems
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 …
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 …
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 …
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 …
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 …
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 …
upon via online convex optimization (OCO). This includes classical techniques such as …