19 citations · 57 across the 18 of their papers we have counts for
3 papers · 1 filter
Sample-Then-Optimize Batch Neural Thompson Sampling
Zhongxiang Dai, Yao Shu, Bryan Kian Hsiang Low +1
Bayesian optimization (BO), which uses a Gaussian process (GP) as a surrogate to model its objective function, is popular for black-box optimization. However, due to the limitation…
Federated Neural Bandits
Zhongxiang Dai, Yao Shu, Arun Verma +3
Recent works on neural contextual bandits have achieved compelling performances due to their ability to leverage the strong representation power of neural networks (NNs) for reward…
Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search
Yao Shu, Zhongxiang Dai, Zhaoxuan Wu +1
Neural architecture search (NAS) has gained immense popularity owing to its ability to automate neural architecture design. A number of training-free metrics are recently proposed…