Multinomial Logit Bandit with Low Switching Cost
Jul 12, 2020
Speakers
Kefan Dong
Speaker · 0 followers
Yingkai Li
Speaker · 0 followers
About
We study multinomial logit bandit with limited adaptivity, where the algorithms change their exploration actions as infrequently as possible when achieving almost optimal minimax regret. We propose two measures of adaptivity: the assortment switching cost and the more fine-grained item switching cost. We present an anytime algorithm (AT-DUCB) with O(N logT) assortment switches, almost matching the lower bound Ω(N logT/ loglogT). In the fixed-horizon setting, our algorithm FH-DUCB incurs O(N loglogT) assortment switches, matching the asymptotic lower bound. We also present the ESUCB algorithm with item switching cost O(N log^2 T).We study multinomial logit bandit with limited adaptivity, where the algorithms change their exploration actions as infrequently as possible when achieving almost optimal minimax regret. We propose two measures of adaptivity: the assortment switching cost and the more fine-grained item switching cost. We present an anytime algorithm (AT-DUCB) with O(N logT) assortment switches, almost matching the lower bound Ω(N logT/ loglogT). In the fixed-horizon setting, our algorithm FH-DUCB incurs O(N logl…
Categories
AI & Data Science
Category · 10.8k presentations
About ICML 2020
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.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Lower Complexity Bounds for Finite-Sum Convex-Concave Minimax Optimization Problems
Watch later
Graph Clustering with Graph Neural Networks
Watch later
Opening remarks
Watch later
Sequence Generation with Mixed Representations
Watch later
Lijun Wu, …
