60 citations · 62 across the 4 of their papers we have counts for
6 papers
Provably Efficient Kernelized Q-Learning
Shuang Liu, Hao Su
We propose and analyze a kernelized version of Q-learning. Although a kernel space is typically infinite-dimensional, extensive study has shown that generalization is only affected…
Task Guided Compositional Representation Learning for ZDA
Shuang Liu, Mete Ozay
Zero-shot domain adaptation (ZDA) methods aim to transfer knowledge about a task learned in a source domain to a target domain, while data from target domain are not available. In…
GQE-PRF: Generative Query Expansion with Pseudo-Relevance Feedback
Minghui Huang, Dong Wang, Shuang Liu +1
Query expansion with pseudo-relevance feedback (PRF) is a powerful approach to enhance the effectiveness in information retrieval. Recently, with the rapid advance of deep learning…
Multi-task Batch Reinforcement Learning with Metric Learning
Jiachen Li, Quan Vuong, Shuang Liu +5
We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks…
The Inductive Bias of Restricted f-GANs
Shuang Liu, Kamalika Chaudhuri
Generative adversarial networks are a novel method for statistical inference that have achieved much empirical success; however, the factors contributing to this success remain ill…
Approximation and Convergence Properties of Generative Adversarial Learning
Shuang Liu, Olivier Bousquet, Kamalika Chaudhuri
Generative adversarial networks (GAN) approximate a target data distribution by jointly optimizing an objective function through a "two-player game" between a generator and a discr…