activity
20172022
most citedApproximation and Convergence Properties of Generative Adversarial Learning

60 citations · 62 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG2022

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…

cs.CV2021

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…

cs.IR20212 cited

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…

cs.LG2019

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…

cs.LG2018

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…

cs.LG201760 cited

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…