Qiang Liu's Publications


Qiang Liu Page Title

Non-asymptotic Confidence Intervals of Off-policy Evaluation: Primal and Dual Bounds.
Y. Feng, Z. Tang, N. Zhang, Q. Liu; ICLR 2021

Varying Coefficient Neural Network with Functional Targeted Regularization for Estimating Continuous Treatment Effects.
L. Nie, M. Ye, Q. Liu, D. Nicolae; ICLR 2021

Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision.
X. Liu, M. Ye, D. Zhou, Q. Liu; AAAI 2021

Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework
D. Zhang*, M. Ye*, C. Gong*, Z. Zhu, Q. Liu; NeurIPS 2020

Certified Monotonic Neural Networks
X. Liu, X. Han, N. Zhang, Q. Liu; NeurIPS 2020

Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks
L. Wu, B. Liu, P. Sone, Q. Liu; NeurIPS 2020

Stein Self-Repulsive Dynamics: Benefits From Past Samples
M. Ye, T. Ren, Q. Liu; NeurIPS 2020

Network Pruning via Greedy Optimization: Fast Rate and Efficient Algorithms
M. Ye, L. Wu, Q. Liu; NeurIPS 2020

Off-Policy Interval Estimation with Lipschitz Value Iteration
Z. Tang, Y. Feng, N. Zhang, J. Peng, Q. Liu; NeurIPS 2020

A General Framework for Empirical Bayes Estimation in Discrete Linear Exponential Family
T. Banerjee, Q. Liu, G. Mukherjee, W. Sun; JMLR 2020

Accountable Off-Policy Evaluation via Kernel Bellman Statistics.
Y. Feng, T. Ren, Z. Tang, Q. Liu; ICML 2020

Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection
M. Ye, G. Gong, L. Nie, D. Zhou, A. Klivans, Q. Liu; ICML 2020

Go Wide, Then Narrow: Efficient Training of Deep Thin Networks
D. Zhou, M. Ye, C. Chen, T. Meng, M. Tan, X. Song, Q. Le, Q. Liu, D. Schuurmans; ICML 2020

A Chance-Constrained Generative Framework for Sequence Optimization
X. Liu, Q. Liu, S. Song, J. Peng; ICML 2020

SAFER: A Structure-free Approach For Certified Robustness to Adversarial Word Substitutions.
M. Ye*, G. Gong*, Q. Liu; ACL 2020

Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation
Z. Tang*, Y. Feng*, L. Li, D. Zhou, Q. Liu; ICLR 2020

Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning
A. Mousavi, L. Li, Q. Liu, D. Zhou; ICLR 2020

Stein Variational Inference for Discrete Distributions
J. Han, F. Ding, X. Liu, L. Torresani, J. Peng, Q. Liu; AISTATS. 2020

Splitting Steepest Descent for Growing Neural Architectures
Q. Liu, D. Wang, L. Wu; NeurIPS 2019

Stein Variational Gradient Descent With Matrix-Valued Kernels
D. Wang, Z. Tang, C. Bajaj, Q. Liu; NeurIPS 2019

A Kernel Loss for Solving the Bellman Equation
Y. Feng, L. Li, Q. Liu; NeurIPS 2019

Exploration via Hindsight Goal Generation
Z. Ren, K. Dong, Y. Zhou , Q. Liu, J. Peng; NeurIPS 2019

Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel.
C. Wei, J.D. Lee, Q. Liu, T. Ma. NeurIps 2019

Mixed Precision Neural Architecture Search for Energy Efficient Deep Learning
C. Gong*, Z. Jiang*, D. Wang, Y. Lin, Q. Liu, D.Z. Pan; ICCAD 2019

Quantile Stein Bayesian Optimization
C. Gong, J. Peng, Q. Liu; ICML 2019

Nonlinear Stein Variational Gradient Descent for Learning Diversified Mixture Models
D. Wang, Q. Liu; ICML 2019

Improving Neural Language Modeling via Adversarial Training
C. Gong*, D. Wang*, Q. Liu; ICML 2019

Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy
Y. Xie, B. Liu, Q. Liu, Z. Wang, Y. Zhou, J. Peng; ICLR 2019

Learning Self-Imitating Diverse Policies
T. Gangwani, Q. Liu, J. Peng; ICLR 2019

LithoROC: Lithography Hotspot Detection with Explicit ROC Optimization
W Ye, Y Lin, M Li, Q Liu, DZ Pan; ASPDAC 2019

Variational Inference with Tail Adaptive f Divergence
Dilin Wang, Hao Liu, Qiang Liu; NeurIPS 2018 (oral)

Stein Variational Gradient Descent as Moment Matching
Qiang Liu, Dilin Wang; NeurIPS 2018

Breaking the Curse of Horizon: Infinite-Horizon Off-policy Estimation
Qiang Liu, Lihong Li, Ziyang Tang, Dengyong Zhou; NeurIPS 2018

Stein Variational Gradient Descent Without Gradient
Jun Han, Qiang Liu; ICML 2018

Stein Variational Message Passing for Continuous Graphical Models
Dilin Wang, Zhe Zeng, Qiang Liu; ICML 2018

Learning to Explore via Meta-Policy Gradient
Tianbing Xu, Liang Zhao, Qiang Liu, Jian Peng; ICML 2018

Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy
Jiasen Yang, Qiang Liu, Vinayak A Rao, Jennifer Neville; ICML 2018

On the Discrimination-Generalization Tradeoff in GANs
P. Zhang, Q. Liu, D. Zhou, T. Xu, X. He; ICLR 2018

Action-dependent Control Variates for Policy Optimization via Stein Identity
H. Liu, Y. Feng, Y. Mao, D. Zhou, J. Peng, Q. Liu; ICLR 2018

Energy-efficient Amortized Inference with Cascaded Deep Classifiers
Jiaqi Guan, Yang Liu, Qiang Liu, Jian Peng; AAAI 2018

Efficient Localized Inference for Large Graphical Models
Jinglin Chen, Jian Peng, Qiang Liu; IJCAI 2018

Stein variational gradient descent as gradient flow
Q. Liu; NeurIPS 2017

Ultra-Low Power Gaze Tracking for Virtual Reality.
T. Li, Q. Liu, and X. Zhou; SenSys 2017 [video]

Stein Variational Policy Gradient
Y. Liu, Ramachandran, Q. Liu, Peng; UAI 2017

Learning to Draw Samples with Amortized Stein Variational Gradient Descent
Feng, Wang, Liu; UAI 2017

Stein Variational Adaptive Importance Sampling
Han, Q. Liu; UAI 2017

Black-box Importance Sampling
Liu, Lee; AISTATS 2017

Local Perturb-and-MAP for Structured Prediction
Bertasius, Liu, Torresani, Shi; AISTATS 2017

Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
Liu, Wang; NeurIPS, 2016. [code]

Bootstrap Model Aggregation for Distributed Statistical Learning
Han, Liu; NeurIPS, 2016.

Learning Infinite RBMs with Frank-Wolfe
Ping, Liu, Ihler; NeurIPS, 2016.

Practical Human Sensing in the Light
Li, Liu, Zhou, MobiSys, 2016 [video] [project page] (SIGMobile Research Highlights)

A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluation
Liu, Lee, Jordan; ICML, 2016. [code: matlab, R]

Efficient Observation Selection in Probabilistic Graphical Models Using Bayesian Lower Bounds
Wang, Fisher, Liu; UAI, 2016.

Importance Weighted Consensus Monte Carlo for Distributed Bayesian Inference
Liu; UAI, 2016.

Communication-Efficient Sparse Regression: a One-Shot Approach
Lee, Liu, Sun, Taylor; JMLR 2016

Probabilistic Variational Bounds for Graphical Models
Liu, Fisher, Ihler; Advances of the Neural Information Processing Systems (NeurIPS) 2015.

Decomposition Bounds for Marginal MAP
Ping, Liu, Ihler; Advances of the Neural Information Processing Systems (NeurIPS) 2015.

Estimating the Partition Function by Discriminance Sampling
Liu, Peng, Ihler, Fisher; Uncertainty in Artificial Intelligence (UAI) 2015.

Boosting Crowdsourcing with Expert Labels: Local vs. Global Effects
Liu, Ihler, Fisher; Int'l Conference on Information Fusion 2015.

Distributed Estimation, Information Loss and Exponential Families
Liu, Ihler; Advances in Neural Information Processing Systems (NeurIPS) 2014.

Aggregating Ordinal Labels from Crowds by Minimax Conditional Entropy
Zhou, Liu, Platt, Meek; International Conference on Machine Learning (ICML), June 2014. [Code] 

CrowdWiFi: Efficient Crowdsensing of Roadside WiFi Networks
Wu, Liu, Zhang, McCann, Regan, Venkatasubramanian; Middleware' 14.

Marginal structured SVM with hidden variables
Ping, Liu, Ihler; International Conference on Machine Learning (ICML), June 2014.

Scoring Workers in Crowdsourcing: How Many Control Questions are Enough?
Liu, Ihler, Steyvers; Advances in Neural Information Processing Systems (NeurIPS) 2013.

Variational Planning for Graph-based MDPs;
Cheng, Liu, Chen, Ihler; Advances in Neural Information Processing Systems (NeurIPS) 2013.

Variational Algorithms for Marginal MAP;
Liu, Ihler; Journal of Machine Learning Research (JMLR) 2013.

Variational Inference for Crowdsourcing;
Liu, Peng, Ihler; Advances in Neural Information Processing Systems (NeurIPS) 2012. [Appendix, Code] 

Brain and muscle Arnt-like protein-1 (BMAL1) controls circadian cell proliferation and susceptibility to UVB-induced DNA damage in the epidermis;
Geyfman M, Kumar V, Liu Q, Ruiz R, Gordon W, Espitia F, Cam E, Millar SE, Smyth P, Ihler A, Takahashi JS, Andersen B; Proc Natl Acad Sci USA doi:10.1073/pnas.120959210 (2012). 

Belief Propagation for Structured Decision Making;
Liu, Ihler; Uncertainty in Artificial Intelligence (UAI) 2012. [Appendix] 

Distributed Parameter Estimation via Pseudo-likelihood;
Liu, Ihler; International Conference on Machine Learning (ICML) 2012. [Appendix] 

Computational Approaches to Sentence Completion;
Geoffrey Zweig, John C. Platt, Christopher Meek, Christopher J.C. Burges, Ainur Yessenalina, and Qiang Liu; in ACL 2012, ACL/SIGPARSE, July 2012.

Variational algorithms for marginal MAP;
Liu, Ihler; Uncertainty in Artificial Intelligence (UAI) 2011. [Full Version] 

Bounding the Partition Function using Holder's Inequality;
Liu, Ihler; International Conference on Machine Learning (ICML) 2011. 

Learning Scale Free Networks by Reweighted l1 Regularization;
Liu, Ihler; AI & Statistics 2010. (notable paper award)

Negative Tree Reweighted Belief Propagation;
Liu, Ihler; Uncertainty in Artificial Intelligence (UAI), July 2010.

Particle Filtered MCMC-MLE with Connections to Contrastive Divergence;
Asuncion, Liu, Ihler, Smyth; Int'l Conf on Machine Learning (ICML), June 2010.

Learning with Blocks: Composite Likelihood and Contrastive Divergence;
Asuncion, Liu, Ihler, Smyth; AI & Statistics (AISTATS), April 2010.

Estimating Replicate Time-Shifts Using Gaussian Process Regression;
Liu, Lin, Anderson, Smyth, Ihler; Bioinformatics 26(6), Mar. 2010, pp. 770-776; doi:10.1093/bioinformatics/btq022.


Qiang Liu Page Title

Approximate Inference with Amortised MCMC
Li, Turner, Liu; https://arxiv.org/abs/1702.08343

Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning
Wang, Liu; https://arxiv.org/pdf/1611.01722

Two Methods for Wild Variational Inference
Liu, Feng; https://arxiv.org/abs/1612.00081