Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tengyuan Liang

Reversible Gromov-Monge Sampler for Simulation-Based Inference


Sep 28, 2021
YoonHaeng Hur, Wenxuan Guo, Tengyuan Liang

* 40 pages, 3 figures 

  Access Paper or Ask Questions

Universal Prediction Band via Semi-Definite Programming


Mar 31, 2021
Tengyuan Liang

* 15 pages, 3 figures 

  Access Paper or Ask Questions

Interpolating Classifiers Make Few Mistakes


Jan 28, 2021
Tengyuan Liang, Benjamin Recht

* 23 pages, 2 figures 

  Access Paper or Ask Questions

Deep Learning for Individual Heterogeneity


Oct 28, 2020
Max H. Farrell, Tengyuan Liang, Sanjog Misra


  Access Paper or Ask Questions

Mehler's Formula, Branching Process, and Compositional Kernels of Deep Neural Networks


Apr 09, 2020
Tengyuan Liang, Hai Tran-Bach


  Access Paper or Ask Questions

A Precise High-Dimensional Asymptotic Theory for Boosting and Min-L1-Norm Interpolated Classifiers


Feb 05, 2020
Tengyuan Liang, Pragya Sur

* 27 pages, 3 figures 

  Access Paper or Ask Questions

Estimating Certain Integral Probability Metric (IPM) is as Hard as Estimating under the IPM


Nov 02, 2019
Tengyuan Liang

* 15 pages. arXiv admin note: substantial text overlap with arXiv:1908.10324 

  Access Paper or Ask Questions

On the Minimax Optimality of Estimating the Wasserstein Metric


Aug 27, 2019
Tengyuan Liang

* 13 pages 

  Access Paper or Ask Questions

On the Risk of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels


Aug 27, 2019
Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai


  Access Paper or Ask Questions

Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits


Jan 21, 2019
Xialiang Dou, Tengyuan Liang

* 24 pages, 5 figures 

  Access Paper or Ask Questions

On How Well Generative Adversarial Networks Learn Densities: Nonparametric and Parametric Results


Nov 07, 2018
Tengyuan Liang

* 31 pages, 3 figures 

  Access Paper or Ask Questions

Deep Neural Networks for Estimation and Inference: Application to Causal Effects and Other Semiparametric Estimands


Sep 26, 2018
Max H. Farrell, Tengyuan Liang, Sanjog Misra


  Access Paper or Ask Questions

Just Interpolate: Kernel "Ridgeless" Regression Can Generalize


Aug 01, 2018
Tengyuan Liang, Alexander Rakhlin

* 18 pages, 3 figures 

  Access Paper or Ask Questions

Local Optimality and Generalization Guarantees for the Langevin Algorithm via Empirical Metastability


Jun 05, 2018
Belinda Tzen, Tengyuan Liang, Maxim Raginsky

* Proceedings of COLT 2018 
* 19 pages 

  Access Paper or Ask Questions

Interaction Matters: A Note on Non-asymptotic Local Convergence of Generative Adversarial Networks


Feb 16, 2018
Tengyuan Liang, James Stokes


  Access Paper or Ask Questions

How Well Can Generative Adversarial Networks Learn Densities: A Nonparametric View


Feb 16, 2018
Tengyuan Liang

* 21 pages 

  Access Paper or Ask Questions

Statistical Inference for the Population Landscape via Moment Adjusted Stochastic Gradients


Dec 20, 2017
Tengyuan Liang, Weijie Su

* 30 pages, 4 figures 

  Access Paper or Ask Questions

Fisher-Rao Metric, Geometry, and Complexity of Neural Networks


Nov 05, 2017
Tengyuan Liang, Tomaso Poggio, Alexander Rakhlin, James Stokes

* 31 pages, 7 figures 

  Access Paper or Ask Questions

Weighted Message Passing and Minimum Energy Flow for Heterogeneous Stochastic Block Models with Side Information


Sep 12, 2017
T. Tony Cai, Tengyuan Liang, Alexander Rakhlin

* 31 pages, 1 figures 

  Access Paper or Ask Questions

Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP


Jun 14, 2017
Satyen Kale, Zohar Karnin, Tengyuan Liang, Dávid Pál

* Appearing in 34th International Conference on Machine Learning (ICML), 2017 

  Access Paper or Ask Questions

On Detection and Structural Reconstruction of Small-World Random Networks


Apr 21, 2016
T. Tony Cai, Tengyuan Liang, Alexander Rakhlin

* 22 pages, 3 figures 

  Access Paper or Ask Questions

Inference via Message Passing on Partially Labeled Stochastic Block Models


Mar 22, 2016
T. Tony Cai, Tengyuan Liang, Alexander Rakhlin

* 33 pages, 4 figures 

  Access Paper or Ask Questions

Computational and Statistical Boundaries for Submatrix Localization in a Large Noisy Matrix


Oct 21, 2015
T. Tony Cai, Tengyuan Liang, Alexander Rakhlin

* 37 pages, 1 figure 

  Access Paper or Ask Questions

Geometric Inference for General High-Dimensional Linear Inverse Problems


Jun 16, 2015
T. Tony Cai, Tengyuan Liang, Alexander Rakhlin

* 39 pages, 6 figures 

  Access Paper or Ask Questions

Learning with Square Loss: Localization through Offset Rademacher Complexity


Jun 15, 2015
Tengyuan Liang, Alexander Rakhlin, Karthik Sridharan

* Journal of Machine Learning Research W&CP vol 40: 1260-1285, 2015 (COLT 2015) 
* 21 pages, 1 figure 

  Access Paper or Ask Questions

Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functions


Jun 15, 2015
Alexandre Belloni, Tengyuan Liang, Hariharan Narayanan, Alexander Rakhlin

* Journal of Machine Learning Research W&CP vol 40: 240-265, 2015 (COLT 2015) 
* 27 pages 

  Access Paper or Ask Questions

On Zeroth-Order Stochastic Convex Optimization via Random Walks


Feb 11, 2014
Tengyuan Liang, Hariharan Narayanan, Alexander Rakhlin

* 10 pages, 3 figures 

  Access Paper or Ask Questions