research
∙
06/13/2023
Fixed-Budget Best-Arm Identification with Heterogeneous Reward Variances
We study the problem of best-arm identification (BAI) in the fixed-budge...
share
research
∙
02/01/2022
Context Uncertainty in Contextual Bandits with Applications to Recommender Systems
Recurrent neural networks have proven effective in modeling sequential u...
research
∙
05/18/2021
Zero-Shot Recommender Systems
Performance of recommender systems (RS) relies heavily on the amount of ...
research
∙
06/08/2019
Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Motivated by the many real-world applications of reinforcement learning ...
research
∙
04/26/2019
Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
With an increasing demand for training powers for deep learning algorith...
research
∙
01/15/2019
Imitation-Regularized Offline Learning
We study the problem of offline learning in automated decision systems u...
research
∙
11/19/2017
Trajectory-Optimized Sensing for Active Search of Tissue Abnormalities in Robotic Surgery
In this work, we develop an approach for guiding robots to automatically...
research
∙
12/02/2016
Active Search for Sparse Signals with Region Sensing
Autonomous systems can be used to search for sparse signals in a large s...
research
∙
09/17/2012