Publications

(*) denotes equal contribution

2024

  1. Preprint
    Sliced Wasserstein with Random-Path Projecting Directions
    Khai Nguyen, Shujian Zhang,  Tam Le and 1 more author
    Under Review
  2. Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning
    Thanh Tung Le, Khai Nguyen,  Shanlin Sun and 2 more authors
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition
  3. ICLRSpotlight
    Quasi-Monte Carlo for 3D Sliced Wasserstein
    Khai Nguyen, Nicolas Bariletto, and Nhat Ho
    International Conference on Learning Representations
    Spotlight Presentation [Top 5%]
  4. Sliced Wasserstein Estimation with Control Variates
    Khai Nguyen, and Nhat Ho
    International Conference on Learning Representations
  5. Diffeomorphic Deformation via Sliced Wasserstein Distance Optimization for Cortical Surface Reconstruction
    Tung Le, Khai NguyenNhat Ho and 3 more authors
    International Conference on Learning Representations
  6. Deep Audio-Text Retrieval Through the Lens of Transportation
    Manh Luong, Khai NguyenNhat Ho and 3 more authors
    International Conference on Learning Representations
  7. AISTATS
    Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts
    Huy Nguyen, Trung Tin Nguyen,  Khai Nguyen and 1 more author
    International Conference on Artificial Intelligence and Statistics
  8. AISTATS
    On Parameter Estimation in Deviated Gaussian Mixture of Experts
    Huy NguyenKhai Nguyen, and Nhat Ho
    International Conference on Artificial Intelligence and Statistics
  9. Fast Approximation of the Generalized Sliced-Wasserstein Distance
    Dung Le*, Huy Nguyen*,  Khai Nguyen* and 2 more authors
    IEEE International Conference on Acoustics, Speech and Signal Processing

2023

  1. Energy-Based Sliced Wasserstein Distance
    Khai Nguyen, and Nhat Ho
    Neural Information Processing Systems
  2. Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models
    Dat Do, Huy NguyenKhai Nguyen and 1 more author
    Neural Information Processing Systems
  3. Markovian Sliced Wasserstein Distances: Beyond Independent Projections
    Khai NguyenTongzheng Ren, and Nhat Ho
    Neural Information Processing Systems
  4. Robustify Transformers with Robust Kernel Density Estimation
    Xing Han, Tongzheng RenTan Nguyen and 3 more authors
    Neural Information Processing Systems
  5. Self-Attention Amortized Distributional Projection Optimization for Sliced Wasserstein Point-Cloud Reconstruction
    Khai Nguyen*, Dang Nguyen*, and Nhat Ho
    International Conference on Machine Learning
  6. Hierarchical Sliced Wasserstein Distance
    Khai NguyenTongzheng RenHuy Nguyen and 3 more authors
    International Conference on Learning Representations
  7. Model Fusion of Heterogeneous Neural Networks via Cross-Layer Alignment
    Dang Nguyen, Trang Nguyen,  Khai Nguyen and 3 more authors
    IEEE International Conference on Acoustics, Speech and Signal Processing

2022

  1. Revisiting Sliced Wasserstein on Images: From Vectorization to Convolution
    Khai Nguyen, and Nhat Ho
    Neural Information Processing Systems
  2. Amortized Projection Optimization for Sliced Wasserstein Generative Models
    Khai Nguyen, and Nhat Ho
    Neural Information Processing Systems
  3. Transformer with Fourier Integral Attentions
    Tan Nguyen, Minh Pham,  Tam Nguyen and 3 more authors
    Neural Information Processing Systems
  4. Improving Transformer with an Admixture of Attention Heads
    Tan Nguyen, Tam Nguyen,  Hai Do and 6 more authors
    Neural Information Processing Systems
  5. Improving Mini-batch Optimal Transport via Partial Transportation
    Khai Nguyen*, Dang Nguyen*,  The-Anh Vu Le and 2 more authors
    In International Conference on Machine Learning
  6. On Transportation of Mini-batches: A Hierarchical Approach
    Khai NguyenDang Nguyen,  Quoc Nguyen and 5 more authors
    In International Conference on Machine Learning
  7. AISTATS
    On Multimarginal Partial Optimal Transport: Equivalent Forms and Computational Complexity
    Khang Le, Huy NguyenKhai Nguyen and 2 more authors
    In International Conference on Artificial Intelligence and Statistics

2021

  1. Structured Dropout Variational Inference for Bayesian Neural Networks
    Son Nguyen, Duong Nguyen,  Khai Nguyen and 3 more authors
    Neural Information Processing Systems
  2. Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
    Khai Nguyen, Son Nguyen,  Nhat Ho and 2 more authors
    In International Conference on Learning Representations
  3. ICLRSpotlight
    Distributional Sliced-Wasserstein and Applications to Generative Modeling
    Khai NguyenNhat Ho,  Tung Pham and 1 more author
    In International Conference on Learning Representations
    Spotlight Presentation [Top 3.78%]