Alert button
Picture for Tengyuan Liang

Tengyuan Liang

Alert button

Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria

Dec 05, 2022
Tengyuan Liang

Figure 1 for Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria
Figure 2 for Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria
Viaarxiv icon

High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models

Apr 09, 2022
Tengyuan Liang, Subhabrata Sen, Pragya Sur

Figure 1 for High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models
Viaarxiv icon

Online Learning to Transport via the Minimal Selection Principle

Feb 09, 2022
Wenxuan Guo, YoonHaeng Hur, Tengyuan Liang, Christopher Ryan

Figure 1 for Online Learning to Transport via the Minimal Selection Principle
Figure 2 for Online Learning to Transport via the Minimal Selection Principle
Figure 3 for Online Learning to Transport via the Minimal Selection Principle
Viaarxiv icon

Reversible Gromov-Monge Sampler for Simulation-Based Inference

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

Figure 1 for Reversible Gromov-Monge Sampler for Simulation-Based Inference
Figure 2 for Reversible Gromov-Monge Sampler for Simulation-Based Inference
Figure 3 for Reversible Gromov-Monge Sampler for Simulation-Based Inference
Viaarxiv icon

Universal Prediction Band via Semi-Definite Programming

Mar 31, 2021
Tengyuan Liang

Figure 1 for Universal Prediction Band via Semi-Definite Programming
Figure 2 for Universal Prediction Band via Semi-Definite Programming
Figure 3 for Universal Prediction Band via Semi-Definite Programming
Figure 4 for Universal Prediction Band via Semi-Definite Programming
Viaarxiv icon

Interpolating Classifiers Make Few Mistakes

Jan 28, 2021
Tengyuan Liang, Benjamin Recht

Figure 1 for Interpolating Classifiers Make Few Mistakes
Figure 2 for Interpolating Classifiers Make Few Mistakes
Viaarxiv icon

Deep Learning for Individual Heterogeneity

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

Figure 1 for Deep Learning for Individual Heterogeneity
Figure 2 for Deep Learning for Individual Heterogeneity
Figure 3 for Deep Learning for Individual Heterogeneity
Figure 4 for Deep Learning for Individual Heterogeneity
Viaarxiv icon

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

Apr 09, 2020
Tengyuan Liang, Hai Tran-Bach

Figure 1 for Mehler's Formula, Branching Process, and Compositional Kernels of Deep Neural Networks
Figure 2 for Mehler's Formula, Branching Process, and Compositional Kernels of Deep Neural Networks
Figure 3 for Mehler's Formula, Branching Process, and Compositional Kernels of Deep Neural Networks
Figure 4 for Mehler's Formula, Branching Process, and Compositional Kernels of Deep Neural Networks
Viaarxiv icon

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

Feb 05, 2020
Tengyuan Liang, Pragya Sur

Figure 1 for A Precise High-Dimensional Asymptotic Theory for Boosting and Min-L1-Norm Interpolated Classifiers
Figure 2 for A Precise High-Dimensional Asymptotic Theory for Boosting and Min-L1-Norm Interpolated Classifiers
Viaarxiv icon

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

Nov 02, 2019
Tengyuan Liang

Viaarxiv icon