Shuang Wu
Shuang Wu
About
Projects
Publications
Light
Dark
Automatic
Projects
Graph Federated Learning
Learning on Graphs (LoG) is widely used in multi-client systems when each client has insufficient local data, and multiple clients have to share their raw data to learn a model of good quality.
Exploration in Bandit Algorithms
We propose a new bootstrap-based online algorithm for stochastic linear bandit problems. The key idea is to adopt residual bootstrap exploration, in which the agent estimates the next step reward by re-sampling the residuals of mean reward estimate.
Cite
×