Predictive Online Convex Optimization
arXiv:1905.06263 · doi:10.1016/j.automatica.2019.108771
Abstract
We incorporate future information in the form of the estimated value of future gradients in online convex optimization. This is motivated by demand response in power systems, where forecasts about the current round, e.g., the weather or the loads' behavior, can be used to improve on predictions made with only past observations. Specifically, we introduce an additional predictive step that follows the standard online convex optimization step when certain conditions on the estimated gradient and descent direction are met. We show that under these conditions and without any assumptions on the predictability of the environment, the predictive update strictly improves on the performance of the standard update. We give two types of predictive update for various family of loss functions. We provide a regret bound for each of our predictive online convex optimization algorithms. Finally, we apply our framework to an example based on demand response which demonstrates its superior performance to a standard online convex optimization algorithm.
References in corpus (10)
- On the Complexity of Best Arm Identification in Multi-Armed Bandit Models
- CVXPY: A Python-Embedded Modeling Language for Convex Optimization
- Artificial Intelligence and Statistics
- Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization
- An Online Convex Optimization Approach to Dynamic Network Resource Allocation
- Bandit Convex Optimization for Scalable and Dynamic IoT Management
- Online Learning with Predictable Sequences
- Optimization, Learning, and Games with Predictable Sequences
- Online Optimization : Competing with Dynamic Comparators
- Setpoint Tracking with Partially Observed Loads