Nhat Ho

35

Papers

60

Total Citations

1

Affiliations

Affiliations

University of Texas, Austin

Papers (35)

Quasi-Monte Carlo for 3D Sliced Wasserstein

Integrating Efficient Optimal Transport and Functional Maps For Unsupervised Shape Correspondence Learning

X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios

Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction

Lightspeed Geometric Dataset Distance via Sliced Optimal Transport

Improving Generalization with Flat Hilbert Bayesian Inference

Attack on Prompt: Backdoor Attack in Prompt-Based Continual Learning

Towards Marginal Fairness Sliced Wasserstein Barycenter

Point-Set Distances for Learning Representations of 3D Point Clouds

Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective

Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features Model

Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?

A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts

On Least Square Estimation in Softmax Gating Mixture of Experts

Sliced Wasserstein with Random-Path Projecting Directions

Improving Computational Complexity in Statistical Models with Local Curvature Information

Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks

Multilevel Clustering via Wasserstein Means

On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms

Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm

Projection Robust Wasserstein Distance and Riemannian Optimization

Structured Dropout Variational Inference for Bayesian Neural Networks

On Robust Optimal Transport: Computational Complexity and Barycenter Computation

Revisiting Sliced Wasserstein on Images: From Vectorization to Convolution

Stochastic Multiple Target Sampling Gradient Descent

Improving Transformer with an Admixture of Attention Heads

Beyond black box densities: Parameter learning for the deviated components

FourierFormer: Transformer Meets Generalized Fourier Integral Theorem

Amortized Projection Optimization for Sliced Wasserstein Generative Models

Demystifying Softmax Gating Function in Gaussian Mixture of Experts

Energy-Based Sliced Wasserstein Distance

LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models

Markovian Sliced Wasserstein Distances: Beyond Independent Projections

Designing Robust Transformers using Robust Kernel Density Estimation