Periodic Updates for Constrained OCO with Application to Large-Scale Multi-Antenna Systems
In many dynamic systems, such as wireless communications, decisions on system operation are updated over time, and the decision maker requires an online learning approach to optimize its strategy in response to the changing environment. When the loss and constraint functions are convex, this belongs to the general family of online convex optimization (OCO). In existing OCO works, the environment is assumed to vary in a time-slotted fashion, while the decisions are updated at each time slot. This model is inadequate for systems that permit only periodic decision updates, i.e., each decision is fixed over multiple time slots, while the environment changes between the decision epochs. In this work, we consider periodic decision updates for OCO. We aim to minimize the accumulation of time-varying convex loss functions, subject to both short-term and long-term constraints. Information about the loss functions within the current update period may be incomplete and is revealed to the decision maker only after the decision is made. We propose an efficient algorithm, termed Periodic Queueing and Gradient Aggregation (PQGA), which employs novel periodic queues together with aggregated gradient descent to update the decisions over time. PQGA is applicable to both constant and time-varying update periods. Most importantly, we show that PQGA yields bounded dynamic regret, static regret, and constraint violation. Furthermore, they are sublinear over time if the accumulated variation of the system states and update periods do not grow too fast. As an example application, we study the performance of PQGA in a large-scale multi-antenna system shared by multiple wireless service providers. Simulation results show that PQGA converges fast and substantially outperforms the known best alternative.?
READ FULL TEXT