5 papers
Balancing Interpretability and Performance in Reinforcement Learning: An Adaptive Spectral Based Linear Approach
Qianxin Yi, Shao-Bo Lin, Jun Fan +1
Reinforcement learning (RL) has been widely applied to sequential decision making, where interpretability and performance are both critical for practical adoption. Current approach…
Efficient Generalized Low-Rank Tensor Contextual Bandits
Qianxin Yi, Yiyang Yang, Shaojie Tang +2
In this paper, we aim to build a novel bandits algorithm that is capable of fully harnessing the power of multi-dimensional data and the inherent non-linearity of reward functions…
Tensor Completion Leveraging Graph Information: A Dynamic Regularization Approach with Statistical Guarantees
Kaidong Wang, Qianxin Yi, Yao Wang +3
We consider the problem of tensor completion with graphs serving as side information to represent interrelationships among variables. Existing approaches suffer from several limita…
An Improved Frequent Directions Algorithm for Low-Rank Approximation via Block Krylov Iteration
Chenhao Wang, Qianxin Yi, Xiuwu Liao +1
Frequent Directions, as a deterministic matrix sketching technique, has been proposed for tackling low-rank approximation problems. This method has a high degree of accuracy and pr…
Effective Streaming Low-tubal-rank Tensor Approximation via Frequent Directions
Qianxin Yi, Chenhao Wang, Kaidong Wang +1
Low-tubal-rank tensor approximation has been proposed to analyze large-scale and multi-dimensional data. However, finding such an accurate approximation is challenging in the strea…