@inproceedings{wang2024coin,
author = {Wang, Lu and Das, Mayukh and Yang, Fangkai and Du, Chao and Qiao, Bo and Dong, Hang and Bansal, Chetan and Qin, Si and Rajmohan, Saravan and 林庆维, Qingwei Lin and Zhang, Dongmei and Zhang, Qi},
title = {COIN: Chance-Constrained Imitation Learning for Safe and Adaptive Resource Oversubscription under Uncertainty},
organization = {ACM},
booktitle = {33rd ACM International Conference on Information and Knowledge Management (CIKM)},
year = {2024},
month = {October},
abstract = {We address the real problem of safe, robust, adaptive resource oversubscription in uncertain environments with our proposed novel technique of chance-constrained imitation learning. Our objective is to enhance resource efficiency while ensuring safety against congestion risk. Traditional supervised or forecasting models are ineffective in learning adaptive oversubscription policies, and conventional online optimization or reinforcement learning is difficult to deploy on real systems. Offline policy learning methods, such as Imitation Learning (IL) can leverage historical resource utilization telemetry data to learn effective policies if we can ensure robustness and safety from the underlying uncertainty in the domain, and thus the data. Our work investigates the nature of this uncertainty, how it can be quantified and proposes a novel chance-constrained IL that implicitly models such uncertainty in a principled manner via additional knowledge in the form of stochastic constraints on the associated risk, to learn provably safe and robust policies. We show empirically a substantial improvement (~ 3-4x) in capacity efficiency and congestion safety in test as well as real deployments.},
url = {http://approjects.co.za/?big=en-us/research/publication/coin-chance-constrained-imitation-learning-for-safe-and-adaptive-resource-oversubscription-under-uncertainty/},
}