Publications

Conferences

Orthogonal Statistical Learning with Self-Concordant Loss
Lang Liu, Carlos Cinelli, Zaid Harchaoui
COLT 2022 (to appear).
PDF  

Entropy Regularized Optimal Transport Independence Criterion
Lang Liu, Soumik Pal, Zaid Harchaoui
AISTATS, 2022 (Oral, top 2.6% of the submissions).
PDF   Code   Poster   Slides  

Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals
Lang Liu, Krishna Pillutla, Sean Welleck, Sewoong Oh, Yejin Choi, Zaid Harchaoui
NeurIPS, 2021.
PDF   Code   Poster   Slides  

Score-Based Change Detection for Gradient-Based Learning Machines
Lang Liu, Joseph Salmon, Zaid Harchaoui
ICASSP, 2021.
PDF-short   PDF-long   Code   Poster   Slides   Video  

Workshops

Discrete Schrödinger Bridges with Applications to Two-Sample Homogeneity Testing
Zaid Harchaoui, Lang Liu, Soumik Pal
NeurIPS OTML Workshop, 2021 (Best Paper Award).
PDF   Slides  

Preprints

Asymptotics of Entropy-Regularized Optimal Transport via Chaos Decomposition
Zaid Harchaoui, Lang Liu, Soumik Pal
Submitted.
PDF   Slides  

Distribution Embedding Networks for Meta-Learning with Heterogeneous Covariate Spaces
Lang Liu, Mahdi Milani Fard, Sen Zhao
Submitted.
PDF