Handling Varied Objectives by Online Decision Making

Conventional machine learning typically assume a fixed learning objective throughout the learning process.However, for real-world tasks in open and dynamic environments, objectives can change frequently.For example, in autonomous driving, a car has several default modes, but a user's concern for speed and fuel consumption varies depending on road conditions and personal needs.We formulate this problem as learning with varied objectives (LVO), where the goal is to optimize a dynamic weighted combination of multiple sub-objectives by sequentially selecting actions that incur different losses on these sub-objectives.We propose the VaRons algorithm, which estimates the action-wise performance on each sub-objective and adaptively selects decisions according to the dynamic requirements on different sub-objectives.Further, we extend our approach to cases involving contextual representations and propose the Con-VaRons algorithm, assuming parameterized linear structure that links contextual features to the main objective.Both the VaRons and ConVaRons are provably minimax optimal with respect to the time horizon , with ConVaRons showing better dependency with the number of sub-objectives .Experiments on dynamic classifier and real-world cluster service allocation tasks validate the effectiveness of our methods and support our theoretical findings. CCS Concepts Computing methodologies Online learning settings.