Jul 12, 2020
We consider a single-product dynamic pricing problem under a specific non-stationary setting, where the demand grows over time in expectation and possibly gets noisier. The decision maker dynamically sets price and learns the unknown price elasticity, with the goal of maximizing expected cumulative revenue. We prove matching upper and lower bounds on regret and provide near-optimal pricing policies. We show how the change in demand uncertainty over time affects the optimal policy design and demonstrate how the order of optimal regret depends on the magnitude of demand uncertainty evolvement. Moreover, we distinguish between the any-time situation and the fixed-time situation by whether the seller knows the total number of time periods T in advance or not, and show that they surprisingly render different optimal regret orders. We then extend the demand model to a more general case allowing for an additional intercept term and present a novel and near-optimal algorithm for the extended model. Finally, we consider an analogous non-stationary setting in the canonical multi-armed bandit problem, and points out that the any-time situation and the fixed-time situation render the same optimal regret order in a simple form, in contrast to the dynamic pricing problem.
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Presentations on similar topic, category or speaker